Package org.lwjgl.cuda

Class CU

java.lang.Object

org.lwjgl.cuda.CU

public class CU
extends Object

Contains bindings to the CUDA Driver API.

Functionality up to CUDA version 3.2, which is the minimum version compatible with the LWJGL bindings, is guaranteed to be available. Functions introduced after CUDA 3.2 may or may not be missing, depending on the CUDA version available at runtime.

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static final class	CU.Functions	Contains the function pointers loaded from the NVCUDA SharedLibrary.

Field Summary

Fields

Modifier and Type	Field	Description
static final int	CU_ACCESS_PROPERTY_NORMAL	Specifies performance hint with CUaccessPolicyWindow for hitProp and missProp members.
static final int	CU_ACCESS_PROPERTY_PERSISTING	Specifies performance hint with CUaccessPolicyWindow for hitProp and missProp members.
static final int	CU_ACCESS_PROPERTY_STREAMING	Specifies performance hint with CUaccessPolicyWindow for hitProp and missProp members.
static final int	CU_AD_FORMAT_BC1_UNORM	Array formats.
static final int	CU_AD_FORMAT_BC1_UNORM_SRGB	Array formats.
static final int	CU_AD_FORMAT_BC2_UNORM	Array formats.
static final int	CU_AD_FORMAT_BC2_UNORM_SRGB	Array formats.
static final int	CU_AD_FORMAT_BC3_UNORM	Array formats.
static final int	CU_AD_FORMAT_BC3_UNORM_SRGB	Array formats.
static final int	CU_AD_FORMAT_BC4_SNORM	Array formats.
static final int	CU_AD_FORMAT_BC4_UNORM	Array formats.
static final int	CU_AD_FORMAT_BC5_SNORM	Array formats.
static final int	CU_AD_FORMAT_BC5_UNORM	Array formats.
static final int	CU_AD_FORMAT_BC6H_SF16	Array formats.
static final int	CU_AD_FORMAT_BC6H_UF16	Array formats.
static final int	CU_AD_FORMAT_BC7_UNORM	Array formats.
static final int	CU_AD_FORMAT_BC7_UNORM_SRGB	Array formats.
static final int	CU_AD_FORMAT_FLOAT	Array formats.
static final int	CU_AD_FORMAT_HALF	Array formats.
static final int	CU_AD_FORMAT_NV12	Array formats.
static final int	CU_AD_FORMAT_SIGNED_INT16	Array formats.
static final int	CU_AD_FORMAT_SIGNED_INT32	Array formats.
static final int	CU_AD_FORMAT_SIGNED_INT8	Array formats.
static final int	CU_AD_FORMAT_SNORM_INT16X1	Array formats.
static final int	CU_AD_FORMAT_SNORM_INT16X2	Array formats.
static final int	CU_AD_FORMAT_SNORM_INT16X4	Array formats.
static final int	CU_AD_FORMAT_SNORM_INT8X1	Array formats.
static final int	CU_AD_FORMAT_SNORM_INT8X2	Array formats.
static final int	CU_AD_FORMAT_SNORM_INT8X4	Array formats.
static final int	CU_AD_FORMAT_UNORM_INT16X1	Array formats.
static final int	CU_AD_FORMAT_UNORM_INT16X2	Array formats.
static final int	CU_AD_FORMAT_UNORM_INT16X4	Array formats.
static final int	CU_AD_FORMAT_UNORM_INT8X1	Array formats.
static final int	CU_AD_FORMAT_UNORM_INT8X2	Array formats.
static final int	CU_AD_FORMAT_UNORM_INT8X4	Array formats.
static final int	CU_AD_FORMAT_UNSIGNED_INT16	Array formats.
static final int	CU_AD_FORMAT_UNSIGNED_INT32	Array formats.
static final int	CU_AD_FORMAT_UNSIGNED_INT8	Array formats.
static final int	CU_ARRAY_SPARSE_PROPERTIES_SINGLE_MIPTAIL	Indicates that the layered sparse CUDA array or CUDA mipmapped array has a single mip tail region for all layers.
static final int	CU_ARRAY_SPARSE_SUBRESOURCE_TYPE_MIPTAIL	Sparse subresource types.
static final int	CU_ARRAY_SPARSE_SUBRESOURCE_TYPE_SPARSE_LEVEL	Sparse subresource types.
static final int	CU_COMPUTEMODE_DEFAULT	Compute Modes.
static final int	CU_COMPUTEMODE_EXCLUSIVE_PROCESS	Compute Modes.
static final int	CU_COMPUTEMODE_PROHIBITED	Compute Modes.
static final int	CU_CTX_BLOCKING_SYNC	Context creation flags.
static final int	CU_CTX_FLAGS_MASK	Context creation flags.
static final int	CU_CTX_LMEM_RESIZE_TO_MAX	Context creation flags.
static final int	CU_CTX_MAP_HOST	Context creation flags.
static final int	CU_CTX_SCHED_AUTO	Context creation flags.
static final int	CU_CTX_SCHED_BLOCKING_SYNC	Context creation flags.
static final int	CU_CTX_SCHED_MASK	Context creation flags.
static final int	CU_CTX_SCHED_SPIN	Context creation flags.
static final int	CU_CTX_SCHED_YIELD	Context creation flags.
static final int	CU_CUBEMAP_FACE_NEGATIVE_X	Array indices for cube faces.
static final int	CU_CUBEMAP_FACE_NEGATIVE_Y	Array indices for cube faces.
static final int	CU_CUBEMAP_FACE_NEGATIVE_Z	Array indices for cube faces.
static final int	CU_CUBEMAP_FACE_POSITIVE_X	Array indices for cube faces.
static final int	CU_CUBEMAP_FACE_POSITIVE_Y	Array indices for cube faces.
static final int	CU_CUBEMAP_FACE_POSITIVE_Z	Array indices for cube faces.
static final int	CU_CUDA_COOPERATIVE_LAUNCH_MULTI_DEVICE_NO_POST_LAUNCH_SYNC	Enum values:
static final int	CU_CUDA_COOPERATIVE_LAUNCH_MULTI_DEVICE_NO_PRE_LAUNCH_SYNC	Enum values:
static final int	CU_DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_CLOCK_RATE	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_COMPUTE_MODE	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_CONCURRENT_KERNELS	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_ECC_ENABLED	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_GPU_OVERLAP	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_INTEGRATED	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_L2_CACHE_SIZE	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_MANAGED_MEMORY	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_MAX_GRID_DIM_X	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_MAX_PITCH	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_MULTI_GPU_BOARD	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_PCI_BUS_ID	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_PCI_DEVICE_ID	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_PCI_DOMAIN_ID	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_TCC_DRIVER	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED	Device properties.
static final int	CU_DEVICE_ATTRIBUTE_WARP_SIZE	Device properties.
static final int	CU_DEVICE_CPU	Device that represents the CPU.
static final int	CU_DEVICE_INVALID	Device that represents an invalid device.
static final int	CU_DEVICE_P2P_ATTRIBUTE_ACCESS_ACCESS_SUPPORTED	P2P Attributes.
static final int	CU_DEVICE_P2P_ATTRIBUTE_ACCESS_SUPPORTED	P2P Attributes.
static final int	CU_DEVICE_P2P_ATTRIBUTE_CUDA_ARRAY_ACCESS_SUPPORTED	P2P Attributes.
static final int	CU_DEVICE_P2P_ATTRIBUTE_NATIVE_ATOMIC_SUPPORTED	P2P Attributes.
static final int	CU_DEVICE_P2P_ATTRIBUTE_PERFORMANCE_RANK	P2P Attributes.
static final int	CU_EVENT_BLOCKING_SYNC	Event creation flags.
static final int	CU_EVENT_DEFAULT	Event creation flags.
static final int	CU_EVENT_DISABLE_TIMING	Event creation flags.
static final int	CU_EVENT_INTERPROCESS	Event creation flags.
static final int	CU_EVENT_RECORD_DEFAULT	Event record flags.
static final int	CU_EVENT_RECORD_EXTERNAL	Event record flags.
static final int	CU_EVENT_WAIT_DEFAULT	Event wait flags.
static final int	CU_EVENT_WAIT_EXTERNAL	Event wait flags.
static final int	CU_EXEC_AFFINITY_TYPE_MAX	Execution Affinity Types
static final int	CU_EXEC_AFFINITY_TYPE_SM_COUNT	Execution Affinity Types
static final int	CU_EXTERNAL_MEMORY_HANDLE_TYPE_D3D11_RESOURCE	External memory handle types.
static final int	CU_EXTERNAL_MEMORY_HANDLE_TYPE_D3D11_RESOURCE_KMT	External memory handle types.
static final int	CU_EXTERNAL_MEMORY_HANDLE_TYPE_D3D12_HEAP	External memory handle types.
static final int	CU_EXTERNAL_MEMORY_HANDLE_TYPE_D3D12_RESOURCE	External memory handle types.
static final int	CU_EXTERNAL_MEMORY_HANDLE_TYPE_NVSCIBUF	External memory handle types.
static final int	CU_EXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_FD	External memory handle types.
static final int	CU_EXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_WIN32	External memory handle types.
static final int	CU_EXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_WIN32_KMT	External memory handle types.
static final int	CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_FENCE	External semaphore handle types.
static final int	CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEX	External semaphore handle types.
static final int	CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEX_KMT	External semaphore handle types.
static final int	CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D12_FENCE	External semaphore handle types.
static final int	CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_NVSCISYNC	External semaphore handle types.
static final int	CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_FD	External semaphore handle types.
static final int	CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32	External semaphore handle types.
static final int	CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32_KMT	External semaphore handle types.
static final int	CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_FD	External semaphore handle types.
static final int	CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_WIN32	External semaphore handle types.
static final int	CU_FLUSH_GPU_DIRECT_RDMA_WRITES_OPTION_HOST	Bitmasks for DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS.
static final int	CU_FLUSH_GPU_DIRECT_RDMA_WRITES_OPTION_MEMOPS	Bitmasks for DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS.
static final int	CU_FLUSH_GPU_DIRECT_RDMA_WRITES_TARGET_CURRENT_CTX	The targets for FlushGPUDirectRDMAWrites (CUflushGPUDirectRDMAWritesTarget)
static final int	CU_FLUSH_GPU_DIRECT_RDMA_WRITES_TO_ALL_DEVICES	The scopes for FlushGPUDirectRDMAWrites (CUflushGPUDirectRDMAWritesScope)
static final int	CU_FLUSH_GPU_DIRECT_RDMA_WRITES_TO_OWNER	The scopes for FlushGPUDirectRDMAWrites (CUflushGPUDirectRDMAWritesScope)
static final int	CU_FUNC_ATTRIBUTE_BINARY_VERSION	Function properties.
static final int	CU_FUNC_ATTRIBUTE_CACHE_MODE_CA	Function properties.
static final int	CU_FUNC_ATTRIBUTE_CONST_SIZE_BYTES	Function properties.
static final int	CU_FUNC_ATTRIBUTE_LOCAL_SIZE_BYTES	Function properties.
static final int	CU_FUNC_ATTRIBUTE_MAX_DYNAMIC_SHARED_SIZE_BYTES	Function properties.
static final int	CU_FUNC_ATTRIBUTE_MAX_THREADS_PER_BLOCK	Function properties.
static final int	CU_FUNC_ATTRIBUTE_NUM_REGS	Function properties.
static final int	CU_FUNC_ATTRIBUTE_PREFERRED_SHARED_MEMORY_CARVEOUT	Function properties.
static final int	CU_FUNC_ATTRIBUTE_PTX_VERSION	Function properties.
static final int	CU_FUNC_ATTRIBUTE_SHARED_SIZE_BYTES	Function properties.
static final int	CU_FUNC_CACHE_PREFER_EQUAL	Function cache configurations.
static final int	CU_FUNC_CACHE_PREFER_L1	Function cache configurations.
static final int	CU_FUNC_CACHE_PREFER_NONE	Function cache configurations.
static final int	CU_FUNC_CACHE_PREFER_SHARED	Function cache configurations.
static final int	CU_GET_PROC_ADDRESS_DEFAULT	Flags to specify search options.
static final int	CU_GET_PROC_ADDRESS_LEGACY_STREAM	Flags to specify search options.
static final int	CU_GET_PROC_ADDRESS_PER_THREAD_DEFAULT_STREAM	Flags to specify search options.
static final int	CU_GPU_DIRECT_RDMA_WRITES_ORDERING_ALL_DEVICES	Platform native ordering for GPUDirect RDMA writes.
static final int	CU_GPU_DIRECT_RDMA_WRITES_ORDERING_NONE	Platform native ordering for GPUDirect RDMA writes.
static final int	CU_GPU_DIRECT_RDMA_WRITES_ORDERING_OWNER	Platform native ordering for GPUDirect RDMA writes.
static final int	CU_GRAPH_DEBUG_DOT_FLAGS_EVENT_NODE_PARAMS	The additional write options for GraphDebugDotPrint (CUgraphDebugDot_flags)
static final int	CU_GRAPH_DEBUG_DOT_FLAGS_EXT_SEMAS_SIGNAL_NODE_PARAMS	The additional write options for GraphDebugDotPrint (CUgraphDebugDot_flags)
static final int	CU_GRAPH_DEBUG_DOT_FLAGS_EXT_SEMAS_WAIT_NODE_PARAMS	The additional write options for GraphDebugDotPrint (CUgraphDebugDot_flags)
static final int	CU_GRAPH_DEBUG_DOT_FLAGS_HANDLES	The additional write options for GraphDebugDotPrint (CUgraphDebugDot_flags)
static final int	CU_GRAPH_DEBUG_DOT_FLAGS_HOST_NODE_PARAMS	The additional write options for GraphDebugDotPrint (CUgraphDebugDot_flags)
static final int	CU_GRAPH_DEBUG_DOT_FLAGS_KERNEL_NODE_ATTRIBUTES	The additional write options for GraphDebugDotPrint (CUgraphDebugDot_flags)
static final int	CU_GRAPH_DEBUG_DOT_FLAGS_KERNEL_NODE_PARAMS	The additional write options for GraphDebugDotPrint (CUgraphDebugDot_flags)
static final int	CU_GRAPH_DEBUG_DOT_FLAGS_MEM_ALLOC_NODE_PARAMS	The additional write options for GraphDebugDotPrint (CUgraphDebugDot_flags)
static final int	CU_GRAPH_DEBUG_DOT_FLAGS_MEM_FREE_NODE_PARAMS	The additional write options for GraphDebugDotPrint (CUgraphDebugDot_flags)
static final int	CU_GRAPH_DEBUG_DOT_FLAGS_MEMCPY_NODE_PARAMS	The additional write options for GraphDebugDotPrint (CUgraphDebugDot_flags)
static final int	CU_GRAPH_DEBUG_DOT_FLAGS_MEMSET_NODE_PARAMS	The additional write options for GraphDebugDotPrint (CUgraphDebugDot_flags)
static final int	CU_GRAPH_DEBUG_DOT_FLAGS_RUNTIME_TYPES	The additional write options for GraphDebugDotPrint (CUgraphDebugDot_flags)
static final int	CU_GRAPH_DEBUG_DOT_FLAGS_VERBOSE	The additional write options for GraphDebugDotPrint (CUgraphDebugDot_flags)
static final int	CU_GRAPH_EXEC_UPDATE_ERROR	CUgraphExecUpdateResult
static final int	CU_GRAPH_EXEC_UPDATE_ERROR_FUNCTION_CHANGED	CUgraphExecUpdateResult
static final int	CU_GRAPH_EXEC_UPDATE_ERROR_NODE_TYPE_CHANGED	CUgraphExecUpdateResult
static final int	CU_GRAPH_EXEC_UPDATE_ERROR_NOT_SUPPORTED	CUgraphExecUpdateResult
static final int	CU_GRAPH_EXEC_UPDATE_ERROR_PARAMETERS_CHANGED	CUgraphExecUpdateResult
static final int	CU_GRAPH_EXEC_UPDATE_ERROR_TOPOLOGY_CHANGED	CUgraphExecUpdateResult
static final int	CU_GRAPH_EXEC_UPDATE_ERROR_UNSUPPORTED_FUNCTION_CHANGE	CUgraphExecUpdateResult
static final int	CU_GRAPH_EXEC_UPDATE_SUCCESS	CUgraphExecUpdateResult
static final int	CU_GRAPH_MEM_ATTR_RESERVED_MEM_CURRENT	CUgraphMem_attribute
static final int	CU_GRAPH_MEM_ATTR_RESERVED_MEM_HIGH	CUgraphMem_attribute
static final int	CU_GRAPH_MEM_ATTR_USED_MEM_CURRENT	CUgraphMem_attribute
static final int	CU_GRAPH_MEM_ATTR_USED_MEM_HIGH	CUgraphMem_attribute
static final int	CU_GRAPH_NODE_TYPE_EMPTY	Graph node types.
static final int	CU_GRAPH_NODE_TYPE_EVENT_RECORD	Graph node types.
static final int	CU_GRAPH_NODE_TYPE_EXT_SEMAS_SIGNAL	Graph node types.
static final int	CU_GRAPH_NODE_TYPE_EXT_SEMAS_WAIT	Graph node types.
static final int	CU_GRAPH_NODE_TYPE_GRAPH	Graph node types.
static final int	CU_GRAPH_NODE_TYPE_HOST	Graph node types.
static final int	CU_GRAPH_NODE_TYPE_KERNEL	Graph node types.
static final int	CU_GRAPH_NODE_TYPE_MEM_ALLOC	Graph node types.
static final int	CU_GRAPH_NODE_TYPE_MEM_FREE	Graph node types.
static final int	CU_GRAPH_NODE_TYPE_MEMCPY	Graph node types.
static final int	CU_GRAPH_NODE_TYPE_MEMSET	Graph node types.
static final int	CU_GRAPH_NODE_TYPE_WAIT_EVENT	Graph node types.
static final int	CU_GRAPH_USER_OBJECT_MOVE	Flags for retaining user object references for graphs.
static final int	CU_GRAPHICS_MAP_RESOURCE_FLAGS_NONE	Flags for mapping and unmapping interop resources.
static final int	CU_GRAPHICS_MAP_RESOURCE_FLAGS_READ_ONLY	Flags for mapping and unmapping interop resources.
static final int	CU_GRAPHICS_MAP_RESOURCE_FLAGS_WRITE_DISCARD	Flags for mapping and unmapping interop resources.
static final int	CU_GRAPHICS_REGISTER_FLAGS_NONE	Flags to register a graphics resource.
static final int	CU_GRAPHICS_REGISTER_FLAGS_READ_ONLY	Flags to register a graphics resource.
static final int	CU_GRAPHICS_REGISTER_FLAGS_SURFACE_LDST	Flags to register a graphics resource.
static final int	CU_GRAPHICS_REGISTER_FLAGS_TEXTURE_GATHER	Flags to register a graphics resource.
static final int	CU_GRAPHICS_REGISTER_FLAGS_WRITE_DISCARD	Flags to register a graphics resource.
static final int	CU_IPC_HANDLE_SIZE
static final int	CU_IPC_MEM_LAZY_ENABLE_PEER_ACCESS	CUDA Ipc Mem Flags.
static final int	CU_JIT_CACHE_MODE	Online compiler and linker options.
static final int	CU_JIT_CACHE_OPTION_CA	Caching modes for dlcm.
static final int	CU_JIT_CACHE_OPTION_CG	Caching modes for dlcm.
static final int	CU_JIT_CACHE_OPTION_NONE	Caching modes for dlcm.
static final int	CU_JIT_ERROR_LOG_BUFFER	Online compiler and linker options.
static final int	CU_JIT_ERROR_LOG_BUFFER_SIZE_BYTES	Online compiler and linker options.
static final int	CU_JIT_FALLBACK_STRATEGY	Online compiler and linker options.
static final int	CU_JIT_FAST_COMPILE	Online compiler and linker options.
static final int	CU_JIT_FMA	Online compiler and linker options.
static final int	CU_JIT_FTZ	Online compiler and linker options.
static final int	CU_JIT_GENERATE_DEBUG_INFO	Online compiler and linker options.
static final int	CU_JIT_GENERATE_LINE_INFO	Online compiler and linker options.
static final int	CU_JIT_GLOBAL_SYMBOL_ADDRESSES	Online compiler and linker options.
static final int	CU_JIT_GLOBAL_SYMBOL_COUNT	Online compiler and linker options.
static final int	CU_JIT_GLOBAL_SYMBOL_NAMES	Online compiler and linker options.
static final int	CU_JIT_INFO_LOG_BUFFER	Online compiler and linker options.
static final int	CU_JIT_INFO_LOG_BUFFER_SIZE_BYTES	Online compiler and linker options.
static final int	CU_JIT_INPUT_CUBIN	Device code formats.
static final int	CU_JIT_INPUT_FATBINARY	Device code formats.
static final int	CU_JIT_INPUT_LIBRARY	Device code formats.
static final int	CU_JIT_INPUT_NVVM	Device code formats.
static final int	CU_JIT_INPUT_OBJECT	Device code formats.
static final int	CU_JIT_INPUT_PTX	Device code formats.
static final int	CU_JIT_LOG_VERBOSE	Online compiler and linker options.
static final int	CU_JIT_LTO	Online compiler and linker options.
static final int	CU_JIT_MAX_REGISTERS	Online compiler and linker options.
static final int	CU_JIT_NEW_SM3X_OPT	Online compiler and linker options.
static final int	CU_JIT_NUM_OPTIONS	Online compiler and linker options.
static final int	CU_JIT_OPTIMIZATION_LEVEL	Online compiler and linker options.
static final int	CU_JIT_PREC_DIV	Online compiler and linker options.
static final int	CU_JIT_PREC_SQRT	Online compiler and linker options.
static final int	CU_JIT_TARGET	Online compiler and linker options.
static final int	CU_JIT_TARGET_FROM_CUCONTEXT	Online compiler and linker options.
static final int	CU_JIT_THREADS_PER_BLOCK	Online compiler and linker options.
static final int	CU_JIT_WALL_TIME	Online compiler and linker options.
static final int	CU_KERNEL_NODE_ATTRIBUTE_ACCESS_POLICY_WINDOW	Graph kernel node Attributes (CUkernelNodeAttrID)
static final int	CU_KERNEL_NODE_ATTRIBUTE_COOPERATIVE	Graph kernel node Attributes (CUkernelNodeAttrID)
static final long	CU_LAUNCH_PARAM_BUFFER_POINTER	Indicator that the next value in the extra parameter to LaunchKernel will be a pointer to a buffer containing all kernel parameters used for launching kernel f.
static final long	CU_LAUNCH_PARAM_BUFFER_SIZE	Indicator that the next value in the extra parameter to LaunchKernel will be a pointer to a size_t which contains the size of the buffer specified with LAUNCH_PARAM_BUFFER_POINTER.
static final long	CU_LAUNCH_PARAM_END	End of array terminator for the extra parameter to LaunchKernel.
static final int	CU_LIMIT_DEV_RUNTIME_PENDING_LAUNCH_COUNT	Limits.
static final int	CU_LIMIT_DEV_RUNTIME_SYNC_DEPTH	Limits.
static final int	CU_LIMIT_MALLOC_HEAP_SIZE	Limits.
static final int	CU_LIMIT_MAX_L2_FETCH_GRANULARITY	Limits.
static final int	CU_LIMIT_PERSISTING_L2_CACHE_SIZE	Limits.
static final int	CU_LIMIT_PRINTF_FIFO_SIZE	Limits.
static final int	CU_LIMIT_STACK_SIZE	Limits.
static final int	CU_MEM_ACCESS_FLAGS_PROT_NONE	Specifies the memory protection flags for mapping.
static final int	CU_MEM_ACCESS_FLAGS_PROT_READ	Specifies the memory protection flags for mapping.
static final int	CU_MEM_ACCESS_FLAGS_PROT_READWRITE	Specifies the memory protection flags for mapping.
static final int	CU_MEM_ADVISE_SET_ACCESSED_BY	Memory advise values.
static final int	CU_MEM_ADVISE_SET_PREFERRED_LOCATION	Memory advise values.
static final int	CU_MEM_ADVISE_SET_READ_MOSTLY	Memory advise values.
static final int	CU_MEM_ADVISE_UNSET_ACCESSED_BY	Memory advise values.
static final int	CU_MEM_ADVISE_UNSET_PREFERRED_LOCATION	Memory advise values.
static final int	CU_MEM_ADVISE_UNSET_READ_MOSTLY	Memory advise values.
static final int	CU_MEM_ALLOC_GRANULARITY_MINIMUM	Flag for requesting different optimal and required granularities for an allocation.
static final int	CU_MEM_ALLOC_GRANULARITY_RECOMMENDED	Flag for requesting different optimal and required granularities for an allocation.
static final int	CU_MEM_ALLOCATION_COMP_GENERIC	Specifies compression attribute for an allocation.
static final int	CU_MEM_ALLOCATION_COMP_NONE	Specifies compression attribute for an allocation.
static final int	CU_MEM_ALLOCATION_TYPE_INVALID	Defines the allocation types available.
static final int	CU_MEM_ALLOCATION_TYPE_PINNED	Defines the allocation types available.
static final int	CU_MEM_ATTACH_GLOBAL	CUDA Mem Attach Flags.
static final int	CU_MEM_ATTACH_HOST	CUDA Mem Attach Flags.
static final int	CU_MEM_ATTACH_SINGLE	CUDA Mem Attach Flags.
static final int	CU_MEM_CREATE_USAGE_TILE_POOL	This flag if set indicates that the memory will be used as a tile pool.
static final int	CU_MEM_HANDLE_TYPE_GENERIC	Memory handle types (CUmemHandleType)
static final int	CU_MEM_HANDLE_TYPE_NONE	Flags for specifying particular handle types.
static final int	CU_MEM_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR	Flags for specifying particular handle types.
static final int	CU_MEM_HANDLE_TYPE_WIN32	Flags for specifying particular handle types.
static final int	CU_MEM_HANDLE_TYPE_WIN32_KMT	Flags for specifying particular handle types.
static final int	CU_MEM_LOCATION_TYPE_DEVICE	Specifies the type of location.
static final int	CU_MEM_LOCATION_TYPE_INVALID	Specifies the type of location.
static final int	CU_MEM_OPERATION_TYPE_MAP	Memory operation types.
static final int	CU_MEM_OPERATION_TYPE_UNMAP	Memory operation types.
static final int	CU_MEM_RANGE_ATTRIBUTE_ACCESSED_BY	(CUmem_range_attribute)
static final int	CU_MEM_RANGE_ATTRIBUTE_LAST_PREFETCH_LOCATION	(CUmem_range_attribute)
static final int	CU_MEM_RANGE_ATTRIBUTE_PREFERRED_LOCATION	(CUmem_range_attribute)
static final int	CU_MEM_RANGE_ATTRIBUTE_READ_MOSTLY	(CUmem_range_attribute)
static final int	CU_MEMHOSTALLOC_DEVICEMAP	Flags for MemHostAlloc.
static final int	CU_MEMHOSTALLOC_PORTABLE	Flags for MemHostAlloc.
static final int	CU_MEMHOSTALLOC_WRITECOMBINED	Flags for MemHostAlloc.
static final int	CU_MEMHOSTREGISTER_DEVICEMAP	Flags for MemHostRegister.
static final int	CU_MEMHOSTREGISTER_IOMEMORY	Flags for MemHostRegister.
static final int	CU_MEMHOSTREGISTER_PORTABLE	Flags for MemHostRegister.
static final int	CU_MEMHOSTREGISTER_READ_ONLY	Flags for MemHostRegister.
static final int	CU_MEMORYTYPE_ARRAY	Memory types.
static final int	CU_MEMORYTYPE_DEVICE	Memory types.
static final int	CU_MEMORYTYPE_HOST	Memory types.
static final int	CU_MEMORYTYPE_UNIFIED	Memory types.
static final int	CU_MEMPOOL_ATTR_RELEASE_THRESHOLD	CUDA memory pool attributes (CUmemPool_attribute)
static final int	CU_MEMPOOL_ATTR_RESERVED_MEM_CURRENT	CUDA memory pool attributes (CUmemPool_attribute)
static final int	CU_MEMPOOL_ATTR_RESERVED_MEM_HIGH	CUDA memory pool attributes (CUmemPool_attribute)
static final int	CU_MEMPOOL_ATTR_REUSE_ALLOW_INTERNAL_DEPENDENCIES	CUDA memory pool attributes (CUmemPool_attribute)
static final int	CU_MEMPOOL_ATTR_REUSE_ALLOW_OPPORTUNISTIC	CUDA memory pool attributes (CUmemPool_attribute)
static final int	CU_MEMPOOL_ATTR_REUSE_FOLLOW_EVENT_DEPENDENCIES	CUDA memory pool attributes (CUmemPool_attribute)
static final int	CU_MEMPOOL_ATTR_USED_MEM_CURRENT	CUDA memory pool attributes (CUmemPool_attribute)
static final int	CU_MEMPOOL_ATTR_USED_MEM_HIGH	CUDA memory pool attributes (CUmemPool_attribute)
static final int	CU_OCCUPANCY_DEFAULT	Occupancy calculator flag.
static final int	CU_OCCUPANCY_DISABLE_CACHING_OVERRIDE	Occupancy calculator flag.
static final int	CU_PARAM_TR_DEFAULT	For texture references loaded into the module, use default texunit from texture reference.
static final int	CU_POINTER_ATTRIBUTE_ACCESS_FLAG_NONE	Access flags that specify the level of access the current context's device has on the memory referenced.
static final int	CU_POINTER_ATTRIBUTE_ACCESS_FLAG_READ	Access flags that specify the level of access the current context's device has on the memory referenced.
static final int	CU_POINTER_ATTRIBUTE_ACCESS_FLAG_READWRITE	Access flags that specify the level of access the current context's device has on the memory referenced.
static final int	CU_POINTER_ATTRIBUTE_ACCESS_FLAGS	Pointer information.
static final int	CU_POINTER_ATTRIBUTE_ALLOWED_HANDLE_TYPES	Pointer information.
static final int	CU_POINTER_ATTRIBUTE_BUFFER_ID	Pointer information.
static final int	CU_POINTER_ATTRIBUTE_CONTEXT	Pointer information.
static final int	CU_POINTER_ATTRIBUTE_DEVICE_ORDINAL	Pointer information.
static final int	CU_POINTER_ATTRIBUTE_DEVICE_POINTER	Pointer information.
static final int	CU_POINTER_ATTRIBUTE_HOST_POINTER	Pointer information.
static final int	CU_POINTER_ATTRIBUTE_IS_GPU_DIRECT_RDMA_CAPABLE	Pointer information.
static final int	CU_POINTER_ATTRIBUTE_IS_LEGACY_CUDA_IPC_CAPABLE	Pointer information.
static final int	CU_POINTER_ATTRIBUTE_IS_MANAGED	Pointer information.
static final int	CU_POINTER_ATTRIBUTE_MAPPED	Pointer information.
static final int	CU_POINTER_ATTRIBUTE_MEMORY_TYPE	Pointer information.
static final int	CU_POINTER_ATTRIBUTE_MEMPOOL_HANDLE	Pointer information.
static final int	CU_POINTER_ATTRIBUTE_P2P_TOKENS	Pointer information.
static final int	CU_POINTER_ATTRIBUTE_RANGE_SIZE	Pointer information.
static final int	CU_POINTER_ATTRIBUTE_RANGE_START_ADDR	Pointer information.
static final int	CU_POINTER_ATTRIBUTE_SYNC_MEMOPS	Pointer information.
static final int	CU_PREFER_BINARY	Cubin matching fallback strategies.
static final int	CU_PREFER_PTX	Cubin matching fallback strategies.
static final int	CU_RES_VIEW_FORMAT_FLOAT_1X16	Resource view format.
static final int	CU_RES_VIEW_FORMAT_FLOAT_1X32	Resource view format.
static final int	CU_RES_VIEW_FORMAT_FLOAT_2X16	Resource view format.
static final int	CU_RES_VIEW_FORMAT_FLOAT_2X32	Resource view format.
static final int	CU_RES_VIEW_FORMAT_FLOAT_4X16	Resource view format.
static final int	CU_RES_VIEW_FORMAT_FLOAT_4X32	Resource view format.
static final int	CU_RES_VIEW_FORMAT_NONE	Resource view format.
static final int	CU_RES_VIEW_FORMAT_SIGNED_BC4	Resource view format.
static final int	CU_RES_VIEW_FORMAT_SIGNED_BC5	Resource view format.
static final int	CU_RES_VIEW_FORMAT_SIGNED_BC6H	Resource view format.
static final int	CU_RES_VIEW_FORMAT_SINT_1X16	Resource view format.
static final int	CU_RES_VIEW_FORMAT_SINT_1X32	Resource view format.
static final int	CU_RES_VIEW_FORMAT_SINT_1X8	Resource view format.
static final int	CU_RES_VIEW_FORMAT_SINT_2X16	Resource view format.
static final int	CU_RES_VIEW_FORMAT_SINT_2X32	Resource view format.
static final int	CU_RES_VIEW_FORMAT_SINT_2X8	Resource view format.
static final int	CU_RES_VIEW_FORMAT_SINT_4X16	Resource view format.
static final int	CU_RES_VIEW_FORMAT_SINT_4X32	Resource view format.
static final int	CU_RES_VIEW_FORMAT_SINT_4X8	Resource view format.
static final int	CU_RES_VIEW_FORMAT_UINT_1X16	Resource view format.
static final int	CU_RES_VIEW_FORMAT_UINT_1X32	Resource view format.
static final int	CU_RES_VIEW_FORMAT_UINT_1X8	Resource view format.
static final int	CU_RES_VIEW_FORMAT_UINT_2X16	Resource view format.
static final int	CU_RES_VIEW_FORMAT_UINT_2X32	Resource view format.
static final int	CU_RES_VIEW_FORMAT_UINT_2X8	Resource view format.
static final int	CU_RES_VIEW_FORMAT_UINT_4X16	Resource view format.
static final int	CU_RES_VIEW_FORMAT_UINT_4X32	Resource view format.
static final int	CU_RES_VIEW_FORMAT_UINT_4X8	Resource view format.
static final int	CU_RES_VIEW_FORMAT_UNSIGNED_BC1	Resource view format.
static final int	CU_RES_VIEW_FORMAT_UNSIGNED_BC2	Resource view format.
static final int	CU_RES_VIEW_FORMAT_UNSIGNED_BC3	Resource view format.
static final int	CU_RES_VIEW_FORMAT_UNSIGNED_BC4	Resource view format.
static final int	CU_RES_VIEW_FORMAT_UNSIGNED_BC5	Resource view format.
static final int	CU_RES_VIEW_FORMAT_UNSIGNED_BC6H	Resource view format.
static final int	CU_RES_VIEW_FORMAT_UNSIGNED_BC7	Resource view format.
static final int	CU_RESOURCE_TYPE_ARRAY	Resource types.
static final int	CU_RESOURCE_TYPE_LINEAR	Resource types.
static final int	CU_RESOURCE_TYPE_MIPMAPPED_ARRAY	Resource types.
static final int	CU_RESOURCE_TYPE_PITCH2D	Resource types.
static final int	CU_SHARED_MEM_CONFIG_DEFAULT_BANK_SIZE	Shared memory configurations.
static final int	CU_SHARED_MEM_CONFIG_EIGHT_BYTE_BANK_SIZE	Shared memory configurations.
static final int	CU_SHARED_MEM_CONFIG_FOUR_BYTE_BANK_SIZE	Shared memory configurations.
static final int	CU_SHAREDMEM_CARVEOUT_DEFAULT	Shared memory carveout configurations.
static final int	CU_SHAREDMEM_CARVEOUT_MAX_L1	Shared memory carveout configurations.
static final int	CU_SHAREDMEM_CARVEOUT_MAX_SHARED	Shared memory carveout configurations.
static final int	CU_STREAM_ADD_CAPTURE_DEPENDENCIES	Flags for StreamUpdateCaptureDependencies).
static final int	CU_STREAM_ATTRIBUTE_ACCESS_POLICY_WINDOW	Stream Attributes (CUstreamAttrID)
static final int	CU_STREAM_ATTRIBUTE_SYNCHRONIZATION_POLICY	Stream Attributes (CUstreamAttrID)
static final int	CU_STREAM_CAPTURE_MODE_GLOBAL	Possible modes for stream capture thread interactions.
static final int	CU_STREAM_CAPTURE_MODE_RELAXED	Possible modes for stream capture thread interactions.
static final int	CU_STREAM_CAPTURE_MODE_THREAD_LOCAL	Possible modes for stream capture thread interactions.
static final int	CU_STREAM_CAPTURE_STATUS_ACTIVE	Possible stream capture statuses returned by StreamIsCapturing.
static final int	CU_STREAM_CAPTURE_STATUS_INVALIDATED	Possible stream capture statuses returned by StreamIsCapturing.
static final int	CU_STREAM_CAPTURE_STATUS_NONE	Possible stream capture statuses returned by StreamIsCapturing.
static final int	CU_STREAM_DEFAULT	Stream creation flags.
static final long	CU_STREAM_LEGACY	Legacy stream handle.
static final int	CU_STREAM_MEM_OP_FLUSH_REMOTE_WRITES	Operations for StreamBatchMemOp.
static final int	CU_STREAM_MEM_OP_WAIT_VALUE_32	Operations for StreamBatchMemOp.
static final int	CU_STREAM_MEM_OP_WAIT_VALUE_64	Operations for StreamBatchMemOp.
static final int	CU_STREAM_MEM_OP_WRITE_VALUE_32	Operations for StreamBatchMemOp.
static final int	CU_STREAM_MEM_OP_WRITE_VALUE_64	Operations for StreamBatchMemOp.
static final int	CU_STREAM_NON_BLOCKING	Stream creation flags.
static final long	CU_STREAM_PER_THREAD	Per-thread stream handle.
static final int	CU_STREAM_SET_CAPTURE_DEPENDENCIES	Flags for StreamUpdateCaptureDependencies).
static final int	CU_STREAM_WAIT_VALUE_AND	Flags for StreamWaitValue32 and StreamWaitValue64.
static final int	CU_STREAM_WAIT_VALUE_EQ	Flags for StreamWaitValue32 and StreamWaitValue64.
static final int	CU_STREAM_WAIT_VALUE_FLUSH	Flags for StreamWaitValue32 and StreamWaitValue64.
static final int	CU_STREAM_WAIT_VALUE_GEQ	Flags for StreamWaitValue32 and StreamWaitValue64.
static final int	CU_STREAM_WAIT_VALUE_NOR	Flags for StreamWaitValue32 and StreamWaitValue64.
static final int	CU_STREAM_WRITE_VALUE_DEFAULT	Flags for StreamWriteValue32.
static final int	CU_STREAM_WRITE_VALUE_NO_MEMORY_BARRIER	Flags for StreamWriteValue32.
static final int	CU_SYNC_POLICY_AUTO	CUsynchronizationPolicy
static final int	CU_SYNC_POLICY_BLOCKING_SYNC	CUsynchronizationPolicy
static final int	CU_SYNC_POLICY_SPIN	CUsynchronizationPolicy
static final int	CU_SYNC_POLICY_YIELD	CUsynchronizationPolicy
static final int	CU_TARGET_COMPUTE_20	Online compilation targets.
static final int	CU_TARGET_COMPUTE_21	Online compilation targets.
static final int	CU_TARGET_COMPUTE_30	Online compilation targets.
static final int	CU_TARGET_COMPUTE_32	Online compilation targets.
static final int	CU_TARGET_COMPUTE_35	Online compilation targets.
static final int	CU_TARGET_COMPUTE_37	Online compilation targets.
static final int	CU_TARGET_COMPUTE_50	Online compilation targets.
static final int	CU_TARGET_COMPUTE_52	Online compilation targets.
static final int	CU_TARGET_COMPUTE_53	Online compilation targets.
static final int	CU_TARGET_COMPUTE_60	Online compilation targets.
static final int	CU_TARGET_COMPUTE_61	Online compilation targets.
static final int	CU_TARGET_COMPUTE_62	Online compilation targets.
static final int	CU_TARGET_COMPUTE_70	Online compilation targets.
static final int	CU_TARGET_COMPUTE_72	Online compilation targets.
static final int	CU_TARGET_COMPUTE_75	Online compilation targets.
static final int	CU_TARGET_COMPUTE_80	Online compilation targets.
static final int	CU_TARGET_COMPUTE_86	Online compilation targets.
static final int	CU_TR_ADDRESS_MODE_BORDER	Texture reference addressing modes.
static final int	CU_TR_ADDRESS_MODE_CLAMP	Texture reference addressing modes.
static final int	CU_TR_ADDRESS_MODE_MIRROR	Texture reference addressing modes.
static final int	CU_TR_ADDRESS_MODE_WRAP	Texture reference addressing modes.
static final int	CU_TR_FILTER_MODE_LINEAR	Texture reference filtering modes.
static final int	CU_TR_FILTER_MODE_POINT	Texture reference filtering modes.
static final int	CU_TRSA_OVERRIDE_FORMAT	Flag for TexRefSetArray.
static final int	CU_TRSF_DISABLE_TRILINEAR_OPTIMIZATION	Flag for TexRefSetFlags.
static final int	CU_TRSF_NORMALIZED_COORDINATES	Flag for TexRefSetFlags.
static final int	CU_TRSF_READ_AS_INTEGER	Flag for TexRefSetFlags.
static final int	CU_TRSF_SRGB	Flag for TexRefSetFlags.
static final int	CU_USER_OBJECT_NO_DESTRUCTOR_SYNC	Flags for user objects for graphs.
static final int	CUDA_ARRAY3D_2DARRAY	Enum values:
static final int	CUDA_ARRAY3D_COLOR_ATTACHMENT	Enum values:
static final int	CUDA_ARRAY3D_CUBEMAP	Enum values:
static final int	CUDA_ARRAY3D_DEPTH_TEXTURE	Enum values:
static final int	CUDA_ARRAY3D_LAYERED	Enum values:
static final int	CUDA_ARRAY3D_SPARSE	Enum values:
static final int	CUDA_ARRAY3D_SURFACE_LDST	Enum values:
static final int	CUDA_ARRAY3D_TEXTURE_GATHER	Enum values:
static final int	CUDA_ERROR_ALREADY_ACQUIRED	Error codes.
static final int	CUDA_ERROR_ALREADY_MAPPED	Error codes.
static final int	CUDA_ERROR_ARRAY_IS_MAPPED	Error codes.
static final int	CUDA_ERROR_ASSERT	Error codes.
static final int	CUDA_ERROR_CAPTURED_EVENT	Error codes.
static final int	CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE	Error codes.
static final int	CUDA_ERROR_CONTEXT_ALREADY_CURRENT	Error codes.
static final int	CUDA_ERROR_CONTEXT_ALREADY_IN_USE	Error codes.
static final int	CUDA_ERROR_CONTEXT_IS_DESTROYED	Error codes.
static final int	CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE	Error codes.
static final int	CUDA_ERROR_DEINITIALIZED	Error codes.
static final int	CUDA_ERROR_DEVICE_NOT_LICENSED	Error codes.
static final int	CUDA_ERROR_ECC_UNCORRECTABLE	Error codes.
static final int	CUDA_ERROR_EXTERNAL_DEVICE	Error codes.
static final int	CUDA_ERROR_FILE_NOT_FOUND	Error codes.
static final int	CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE	Error codes.
static final int	CUDA_ERROR_HARDWARE_STACK_ERROR	Error codes.
static final int	CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED	Error codes.
static final int	CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED	Error codes.
static final int	CUDA_ERROR_ILLEGAL_ADDRESS	Error codes.
static final int	CUDA_ERROR_ILLEGAL_INSTRUCTION	Error codes.
static final int	CUDA_ERROR_ILLEGAL_STATE	Error codes.
static final int	CUDA_ERROR_INVALID_ADDRESS_SPACE	Error codes.
static final int	CUDA_ERROR_INVALID_CONTEXT	Error codes.
static final int	CUDA_ERROR_INVALID_DEVICE	Error codes.
static final int	CUDA_ERROR_INVALID_GRAPHICS_CONTEXT	Error codes.
static final int	CUDA_ERROR_INVALID_HANDLE	Error codes.
static final int	CUDA_ERROR_INVALID_IMAGE	Error codes.
static final int	CUDA_ERROR_INVALID_PC	Error codes.
static final int	CUDA_ERROR_INVALID_PTX	Error codes.
static final int	CUDA_ERROR_INVALID_SOURCE	Error codes.
static final int	CUDA_ERROR_INVALID_VALUE	Error codes.
static final int	CUDA_ERROR_JIT_COMPILATION_DISABLED	Error codes.
static final int	CUDA_ERROR_JIT_COMPILER_NOT_FOUND	Error codes.
static final int	CUDA_ERROR_LAUNCH_FAILED	Error codes.
static final int	CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING	Error codes.
static final int	CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES	Error codes.
static final int	CUDA_ERROR_LAUNCH_TIMEOUT	Error codes.
static final int	CUDA_ERROR_MAP_FAILED	Error codes.
static final int	CUDA_ERROR_MISALIGNED_ADDRESS	Error codes.
static final int	CUDA_ERROR_MPS_CONNECTION_FAILED	Error codes.
static final int	CUDA_ERROR_MPS_MAX_CLIENTS_REACHED	Error codes.
static final int	CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED	Error codes.
static final int	CUDA_ERROR_MPS_RPC_FAILURE	Error codes.
static final int	CUDA_ERROR_MPS_SERVER_NOT_READY	Error codes.
static final int	CUDA_ERROR_NO_BINARY_FOR_GPU	Error codes.
static final int	CUDA_ERROR_NO_DEVICE	Error codes.
static final int	CUDA_ERROR_NOT_FOUND	Error codes.
static final int	CUDA_ERROR_NOT_INITIALIZED	Error codes.
static final int	CUDA_ERROR_NOT_MAPPED	Error codes.
static final int	CUDA_ERROR_NOT_MAPPED_AS_ARRAY	Error codes.
static final int	CUDA_ERROR_NOT_MAPPED_AS_POINTER	Error codes.
static final int	CUDA_ERROR_NOT_PERMITTED	Error codes.
static final int	CUDA_ERROR_NOT_READY	Error codes.
static final int	CUDA_ERROR_NOT_SUPPORTED	Error codes.
static final int	CUDA_ERROR_NVLINK_UNCORRECTABLE	Error codes.
static final int	CUDA_ERROR_OPERATING_SYSTEM	Error codes.
static final int	CUDA_ERROR_OUT_OF_MEMORY	Error codes.
static final int	CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED	Error codes.
static final int	CUDA_ERROR_PEER_ACCESS_NOT_ENABLED	Error codes.
static final int	CUDA_ERROR_PEER_ACCESS_UNSUPPORTED	Error codes.
static final int	CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE	Error codes.
static final int	CUDA_ERROR_PROFILER_ALREADY_STARTED	Error codes.
static final int	CUDA_ERROR_PROFILER_ALREADY_STOPPED	Error codes.
static final int	CUDA_ERROR_PROFILER_DISABLED	Error codes.
static final int	CUDA_ERROR_PROFILER_NOT_INITIALIZED	Error codes.
static final int	CUDA_ERROR_SHARED_OBJECT_INIT_FAILED	Error codes.
static final int	CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND	Error codes.
static final int	CUDA_ERROR_STREAM_CAPTURE_IMPLICIT	Error codes.
static final int	CUDA_ERROR_STREAM_CAPTURE_INVALIDATED	Error codes.
static final int	CUDA_ERROR_STREAM_CAPTURE_ISOLATION	Error codes.
static final int	CUDA_ERROR_STREAM_CAPTURE_MERGE	Error codes.
static final int	CUDA_ERROR_STREAM_CAPTURE_UNJOINED	Error codes.
static final int	CUDA_ERROR_STREAM_CAPTURE_UNMATCHED	Error codes.
static final int	CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED	Error codes.
static final int	CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD	Error codes.
static final int	CUDA_ERROR_STUB_LIBRARY	Error codes.
static final int	CUDA_ERROR_SYSTEM_DRIVER_MISMATCH	Error codes.
static final int	CUDA_ERROR_SYSTEM_NOT_READY	Error codes.
static final int	CUDA_ERROR_TIMEOUT	Error codes.
static final int	CUDA_ERROR_TOO_MANY_PEERS	Error codes.
static final int	CUDA_ERROR_UNKNOWN	Error codes.
static final int	CUDA_ERROR_UNMAP_FAILED	Error codes.
static final int	CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY	Error codes.
static final int	CUDA_ERROR_UNSUPPORTED_LIMIT	Error codes.
static final int	CUDA_ERROR_UNSUPPORTED_PTX_VERSION	Error codes.
static final int	CUDA_EXTERNAL_MEMORY_DEDICATED	Indicates that the external memory object is a dedicated resource.
static final int	CUDA_EXTERNAL_SEMAPHORE_SIGNAL_SKIP_NVSCIBUF_MEMSYNC	When the flags parameter of CUDA_EXTERNAL_SEMAPHORE_SIGNAL_PARAMS contains this flag, it indicates that signaling an external semaphore object should skip performing appropriate memory synchronization operations over all the external memory objects that are imported as EXTERNAL_MEMORY_HANDLE_TYPE_NVSCIBUF, which otherwise are performed by default to ensure data coherency with other importers of the same NvSciBuf memory objects.
static final int	CUDA_EXTERNAL_SEMAPHORE_WAIT_SKIP_NVSCIBUF_MEMSYNC	When the flags parameter of CUDA_EXTERNAL_SEMAPHORE_WAIT_PARAMS contains this flag, it indicates that waiting on an external semaphore object should skip performing appropriate memory synchronization operations over all the external memory objects that are imported as EXTERNAL_MEMORY_HANDLE_TYPE_NVSCIBUF, which otherwise are performed by default to ensure data coherency with other importers of the same NvSciBuf memory objects.
static final int	CUDA_GRAPH_INSTANTIATE_FLAG_AUTO_FREE_ON_LAUNCH	Flags for instantiating a graph.
static final int	CUDA_NVSCISYNC_ATTR_SIGNAL	When flags of DeviceGetNvSciSyncAttributes is set to this, it indicates that application needs signaler specific NvSciSyncAttr to be filled by cuDeviceGetNvSciSyncAttributes.
static final int	CUDA_NVSCISYNC_ATTR_WAIT	When flags of DeviceGetNvSciSyncAttributes is set to this, it indicates that application needs waiter specific NvSciSyncAttr to be filled by cuDeviceGetNvSciSyncAttributes.
static final int	CUDA_SUCCESS	Error codes.

Method Summary

Modifier and Type	Method	Description
static int	cuArray3DCreate(PointerBuffer pHandle, CUDA_ARRAY3D_DESCRIPTOR pAllocateArray)	Creates a 3D CUDA array.
static int	cuArray3DGetDescriptor(CUDA_ARRAY3D_DESCRIPTOR pArrayDescriptor, long hArray)	Get a 3D CUDA array descriptor.
static int	cuArrayCreate(PointerBuffer pHandle, CUDA_ARRAY_DESCRIPTOR pAllocateArray)	Creates a 1D or 2D CUDA array.
static int	cuArrayDestroy(long hArray)	Destroys a CUDA array.
static int	cuArrayGetDescriptor(CUDA_ARRAY_DESCRIPTOR pArrayDescriptor, long hArray)	Get a 1D or 2D CUDA array descriptor.
static int	cuArrayGetPlane(PointerBuffer pPlaneArray, long hArray, int planeIdx)	Gets a CUDA array plane from a CUDA array.
static int	cuArrayGetSparseProperties(CUDA_ARRAY_SPARSE_PROPERTIES sparseProperties, long array)	Returns the layout properties of a sparse CUDA array.
static int	cuCtxAttach(PointerBuffer pctx, int flags)	Increment a context's usage-count.
static int	cuCtxCreate(PointerBuffer pctx, int flags, int dev)	Create a CUDA context.
static int	cuCtxCreate_v3(PointerBuffer pctx, CUexecAffinityParam.Buffer paramsArray, int flags, int dev)	Create a CUDA context with execution affinity.
static int	cuCtxDestroy(long ctx)	Destroy a CUDA context.
static int	cuCtxDetach(long ctx)	Decrement a context's usage-count
static int	cuCtxDisablePeerAccess(long peerContext)	Disables direct access to memory allocations in a peer context and unregisters any registered allocations.
static int	cuCtxEnablePeerAccess(long peerContext, int Flags)	Enables direct access to memory allocations in a peer context.
static int	cuCtxGetApiVersion(long ctx, IntBuffer version)	Gets the context's API version.
static int	cuCtxGetCacheConfig(IntBuffer pconfig)	Returns the preferred cache configuration for the current context.
static int	cuCtxGetCurrent(PointerBuffer pctx)	Returns the CUDA context bound to the calling CPU thread.
static int	cuCtxGetDevice(IntBuffer device)	Returns the device ID for the current context.
static int	cuCtxGetExecAffinity(CUexecAffinityParam.Buffer pExecAffinity, int type)	Returns the execution affinity setting for the current context.
static int	cuCtxGetFlags(IntBuffer flags)	Returns the flags for the current context.
static int	cuCtxGetLimit(PointerBuffer pvalue, int limit)	Returns resource limits.
static int	cuCtxGetSharedMemConfig(IntBuffer pConfig)	Returns the current shared memory configuration for the current context.
static int	cuCtxGetStreamPriorityRange(IntBuffer leastPriority, IntBuffer greatestPriority)	Returns numerical values that correspond to the least and greatest stream priorities.
static int	cuCtxPopCurrent(PointerBuffer pctx)	Pops the current CUDA context from the current CPU thread.
static int	cuCtxPushCurrent(long ctx)	Pushes a context on the current CPU thread.
static int	cuCtxResetPersistingL2Cache()	Resets all persisting lines in cache to normal status.
static int	cuCtxSetCacheConfig(int config)	Sets the preferred cache configuration for the current context.
static int	cuCtxSetCurrent(long ctx)	Binds the specified CUDA context to the calling CPU thread.
static int	cuCtxSetLimit(int limit, long value)	Set resource limits.
static int	cuCtxSetSharedMemConfig(int config)	Sets the shared memory configuration for the current context.
static int	cuCtxSynchronize()	Block for a context's tasks to complete.
static int	cuDestroyExternalMemory(long extMem)	Destroys an external memory object.
static int	cuDestroyExternalSemaphore(long extSem)	Destroys an external semaphore.
static int	cuDeviceCanAccessPeer(IntBuffer canAccessPeer, int dev, int peerDev)	Queries if a device may directly access a peer device's memory.
static int	cuDeviceComputeCapability(IntBuffer major, IntBuffer minor, int dev)	Returns the compute capability of the device.
static int	cuDeviceGet(IntBuffer device, int ordinal)	Returns a handle to a compute device.
static int	cuDeviceGetAttribute(IntBuffer pi, int attrib, int dev)	Returns information about the device.
static int	cuDeviceGetByPCIBusId(IntBuffer dev, CharSequence pciBusId)	Returns a handle to a compute device.
static int	cuDeviceGetByPCIBusId(IntBuffer dev, ByteBuffer pciBusId)	Returns a handle to a compute device.
static int	cuDeviceGetCount(IntBuffer count)	Returns the number of compute-capable devices.
static int	cuDeviceGetDefaultMemPool(PointerBuffer pool_out, int dev)	Returns the default mempool of a device.
static int	cuDeviceGetExecAffinitySupport(IntBuffer pi, int type, int dev)	Returns information about the execution affinity support of the device.
static int	cuDeviceGetGraphMemAttribute(int device, int attr, ByteBuffer value)	Query asynchronous allocation attributes related to graphs.
static int	cuDeviceGetGraphMemAttribute(int device, int attr, LongBuffer value)	Query asynchronous allocation attributes related to graphs.
static int	cuDeviceGetLuid(ByteBuffer luid, IntBuffer deviceNodeMask, int dev)	Return an LUID and device node mask for the device
static int	cuDeviceGetMemPool(PointerBuffer pool, int dev)	Gets the current mempool for a device.
static int	cuDeviceGetName(ByteBuffer name, int dev)	Returns an identifer string for the device.
static int	cuDeviceGetNvSciSyncAttributes(ByteBuffer nvSciSyncAttrList, int dev, int flags)	Return NvSciSync attributes that this device can support.
static int	cuDeviceGetP2PAttribute(IntBuffer value, int attrib, int srcDevice, int dstDevice)	Queries attributes of the link between two devices.
static int	cuDeviceGetPCIBusId(ByteBuffer pciBusId, int dev)	Returns a PCI Bus Id string for the device.
static int	cuDeviceGetProperties(CUdevprop prop, int dev)	Returns properties for a selected device.
static int	cuDeviceGetTexture1DLinearMaxWidth(PointerBuffer maxWidthInElements, int format, int numChannels, int dev)	Returns the maximum number of elements allocatable in a 1D linear texture for a given texture element size.
static int	cuDeviceGetUuid(CUuuid uuid, int dev)	Return an UUID for the device.
static int	cuDeviceGetUuid_v2(CUuuid uuid, int dev)	Return an UUID for the device (11.4+).
static int	cuDeviceGraphMemTrim(int device)	Free unused memory that was cached on the specified device for use with graphs back to the OS.
static int	cuDevicePrimaryCtxGetState(int dev, IntBuffer flags, IntBuffer active)	Get the state of the primary context.
static int	cuDevicePrimaryCtxRelease(int dev)	Release the primary context on the GPU.
static int	cuDevicePrimaryCtxReset(int dev)	Destroy all allocations and reset all state on the primary context.
static int	cuDevicePrimaryCtxRetain(PointerBuffer pctx, int dev)	Retain the primary context on the GPU.
static int	cuDevicePrimaryCtxSetFlags(int dev, int flags)	Set flags for the primary context.
static int	cuDeviceSetGraphMemAttribute(int device, int attr, ByteBuffer value)	Set asynchronous allocation attributes related to graphs.
static int	cuDeviceSetGraphMemAttribute(int device, int attr, LongBuffer value)	Set asynchronous allocation attributes related to graphs.
static int	cuDeviceSetMemPool(int dev, long pool)	Sets the current memory pool of a device
static int	cuDeviceTotalMem(PointerBuffer bytes, int dev)	Returns the total amount of memory on the device
static int	cuDriverGetVersion(IntBuffer driverVersion)	Returns the latest CUDA version supported by driver.
static int	cuEventCreate(PointerBuffer phEvent, int Flags)	Creates an event.
static int	cuEventDestroy(long hEvent)	Destroys an event.
static int	cuEventElapsedTime(FloatBuffer pMilliseconds, long hStart, long hEnd)	Computes the elapsed time between two events.
static int	cuEventQuery(long hEvent)	Queries an event's status.
static int	cuEventRecord(long hEvent, long hStream)	Records an event.
static int	cuEventRecordWithFlags(long hEvent, long hStream, int flags)	Records an event.
static int	cuEventSynchronize(long hEvent)	Waits for an event to complete.
static int	cuExternalMemoryGetMappedBuffer(PointerBuffer devPtr, long extMem, CUDA_EXTERNAL_MEMORY_BUFFER_DESC bufferDesc)	Maps a buffer onto an imported memory object.
static int	cuExternalMemoryGetMappedMipmappedArray(PointerBuffer mipmap, long extMem, CUDA_EXTERNAL_MEMORY_MIPMAPPED_ARRAY_DESC mipmapDesc)	Maps a CUDA mipmapped array onto an external memory object.
static int	cuFlushGPUDirectRDMAWrites(int target, int scope)	Blocks until remote writes are visible to the specified scope.
static int	cuFuncGetAttribute(IntBuffer pi, int attrib, long hfunc)	Returns information about a function.
static int	cuFuncGetModule(PointerBuffer hmod, long hfunc)	Returns a module handle.
static int	cuFuncSetAttribute(long hfunc, int attrib, int value)	Sets information about a function.
static int	cuFuncSetBlockShape(long hfunc, int x, int y, int z)	Sets the block-dimensions for the function.
static int	cuFuncSetCacheConfig(long hfunc, int config)	Sets the preferred cache configuration for a device function.
static int	cuFuncSetSharedMemConfig(long hfunc, int config)	Sets the shared memory configuration for a device function.
static int	cuFuncSetSharedSize(long hfunc, int bytes)	Sets the dynamic shared-memory size for the function.
static int	cuGetErrorName(int error, PointerBuffer pStr)	Gets the string representation of an error code enum name.
static int	cuGetErrorString(int error, PointerBuffer pStr)	Gets the string description of an error code.
static int	cuGetExportTable(PointerBuffer ppExportTable, CUuuid pExportTableId)
static int	cuGetProcAddress(CharSequence symbol, PointerBuffer pfn, int cudaVersion, long flags)	Returns the requested driver API function pointer.
static int	cuGetProcAddress(ByteBuffer symbol, PointerBuffer pfn, int cudaVersion, long flags)	Returns the requested driver API function pointer.
static int	cuGraphAddChildGraphNode(PointerBuffer phGraphNode, long hGraph, PointerBuffer dependencies, long childGraph)	Creates a child graph node and adds it to a graph.
static int	cuGraphAddDependencies(long hGraph, PointerBuffer from, PointerBuffer to)	Adds dependency edges to a graph.
static int	cuGraphAddEmptyNode(PointerBuffer phGraphNode, long hGraph, PointerBuffer dependencies)	Creates an empty node and adds it to a graph.
static int	cuGraphAddEventRecordNode(PointerBuffer phGraphNode, long hGraph, PointerBuffer dependencies, long event)	Creates an event record node and adds it to a graph.
static int	cuGraphAddEventWaitNode(PointerBuffer phGraphNode, long hGraph, PointerBuffer dependencies, long event)	Creates an event wait node and adds it to a graph.
static int	cuGraphAddExternalSemaphoresSignalNode(PointerBuffer phGraphNode, long hGraph, PointerBuffer dependencies, CUDA_EXT_SEM_SIGNAL_NODE_PARAMS nodeParams)	Creates an external semaphore signal node and adds it to a graph.
static int	cuGraphAddExternalSemaphoresWaitNode(PointerBuffer phGraphNode, long hGraph, PointerBuffer dependencies, CUDA_EXT_SEM_WAIT_NODE_PARAMS nodeParams)	Creates an external semaphore wait node and adds it to a graph.
static int	cuGraphAddHostNode(PointerBuffer phGraphNode, long hGraph, PointerBuffer dependencies, CUDA_HOST_NODE_PARAMS nodeParams)	Creates a host execution node and adds it to a graph.
static int	cuGraphAddKernelNode(PointerBuffer phGraphNode, long hGraph, PointerBuffer dependencies, CUDA_KERNEL_NODE_PARAMS nodeParams)	Creates a kernel execution node and adds it to a graph.
static int	cuGraphAddMemAllocNode(PointerBuffer phGraphNode, long hGraph, PointerBuffer dependencies, CUDA_MEM_ALLOC_NODE_PARAMS nodeParams)	Creates an allocation node and adds it to a graph.
static int	cuGraphAddMemcpyNode(PointerBuffer phGraphNode, long hGraph, PointerBuffer dependencies, CUDA_MEMCPY3D copyParams, long ctx)	Creates a memcpy node and adds it to a graph.
static int	cuGraphAddMemFreeNode(PointerBuffer phGraphNode, long hGraph, PointerBuffer dependencies, long dptr)	Creates a memory free node and adds it to a graph.
static int	cuGraphAddMemsetNode(PointerBuffer phGraphNode, long hGraph, PointerBuffer dependencies, CUDA_MEMSET_NODE_PARAMS memsetParams, long ctx)	Creates a memset node and adds it to a graph.
static int	cuGraphChildGraphNodeGetGraph(long hNode, PointerBuffer phGraph)	Gets a handle to the embedded graph of a child graph node.
static int	cuGraphClone(PointerBuffer phGraphClone, long originalGraph)	Clones a graph.
static int	cuGraphCreate(PointerBuffer phGraph, int flags)	Creates a graph.
static int	cuGraphDebugDotPrint(long hGraph, CharSequence path, int flags)	Write a DOT file describing graph structure.
static int	cuGraphDebugDotPrint(long hGraph, ByteBuffer path, int flags)	Write a DOT file describing graph structure.
static int	cuGraphDestroy(long hGraph)	Destroys a graph.
static int	cuGraphDestroyNode(long hNode)	Remove a node from the graph.
static int	cuGraphEventRecordNodeGetEvent(long hNode, PointerBuffer event_out)	Returns the event associated with an event record node.
static int	cuGraphEventRecordNodeSetEvent(long hNode, long event)	Sets an event record node's event.
static int	cuGraphEventWaitNodeGetEvent(long hNode, PointerBuffer event_out)	Returns the event associated with an event wait node.
static int	cuGraphEventWaitNodeSetEvent(long hNode, long event)	Sets an event wait node's event.
static int	cuGraphExecChildGraphNodeSetParams(long hGraphExec, long hNode, long childGraph)	Updates node parameters in the child graph node in the given graphExec.
static int	cuGraphExecDestroy(long hGraphExec)	Destroys an executable graph.
static int	cuGraphExecEventRecordNodeSetEvent(long hGraphExec, long hNode, long event)	Sets the event for an event record node in the given graphExec.
static int	cuGraphExecEventWaitNodeSetEvent(long hGraphExec, long hNode, long event)	Sets the event for an event wait node in the given graphExec.
static int	cuGraphExecExternalSemaphoresSignalNodeSetParams(long hGraphExec, long hNode, CUDA_EXT_SEM_SIGNAL_NODE_PARAMS nodeParams)	Sets the parameters for an external semaphore signal node in the given graphExec.
static int	cuGraphExecExternalSemaphoresWaitNodeSetParams(long hGraphExec, long hNode, CUDA_EXT_SEM_WAIT_NODE_PARAMS nodeParams)	Sets the parameters for an external semaphore wait node in the given graphExec.
static int	cuGraphExecHostNodeSetParams(long hGraphExec, long hNode, CUDA_HOST_NODE_PARAMS nodeParams)	Sets the parameters for a host node in the given graphExec.
static int	cuGraphExecKernelNodeSetParams(long hGraphExec, long hNode, CUDA_KERNEL_NODE_PARAMS nodeParams)	Sets the parameters for a kernel node in the given graphExec.
static int	cuGraphExecMemcpyNodeSetParams(long hGraphExec, long hNode, CUDA_MEMCPY3D copyParams, long ctx)	Sets the parameters for a memcpy node in the given graphExec.
static int	cuGraphExecMemsetNodeSetParams(long hGraphExec, long hNode, CUDA_MEMSET_NODE_PARAMS memsetParams, long ctx)	Sets the parameters for a memset node in the given graphExec.
static int	cuGraphExecUpdate(long hGraphExec, long hGraph, PointerBuffer hErrorNode_out, IntBuffer updateResult_out)	Check whether an executable graph can be updated with a graph and perform the update if possible.
static int	cuGraphExternalSemaphoresSignalNodeGetParams(long hNode, CUDA_EXT_SEM_SIGNAL_NODE_PARAMS params_out)	Returns an external semaphore signal node's parameters.
static int	cuGraphExternalSemaphoresSignalNodeSetParams(long hNode, CUDA_EXT_SEM_SIGNAL_NODE_PARAMS nodeParams)	Sets an external semaphore signal node's parameters.
static int	cuGraphExternalSemaphoresWaitNodeGetParams(long hNode, CUDA_EXT_SEM_WAIT_NODE_PARAMS params_out)	Returns an external semaphore wait node's parameters.
static int	cuGraphExternalSemaphoresWaitNodeSetParams(long hNode, CUDA_EXT_SEM_WAIT_NODE_PARAMS nodeParams)	Sets an external semaphore wait node's parameters.
static int	cuGraphGetEdges(long hGraph, PointerBuffer from, PointerBuffer to, PointerBuffer numEdges)	Returns a graph's dependency edges.
static int	cuGraphGetNodes(long hGraph, PointerBuffer nodes, PointerBuffer numNodes)	Returns a graph's nodes.
static int	cuGraphGetRootNodes(long hGraph, PointerBuffer rootNodes, PointerBuffer numRootNodes)	Returns a graph's root nodes.
static int	cuGraphHostNodeGetParams(long hNode, CUDA_HOST_NODE_PARAMS nodeParams)	Returns a host node's parameters.
static int	cuGraphHostNodeSetParams(long hNode, CUDA_HOST_NODE_PARAMS nodeParams)	Sets a host node's parameters.
static int	cuGraphicsMapResources(PointerBuffer resources, long hStream)	Map graphics resources for access by CUDA.
static int	cuGraphicsResourceGetMappedMipmappedArray(PointerBuffer pMipmappedArray, long resource)	Get a mipmapped array through which to access a mapped graphics resource.
static int	cuGraphicsResourceGetMappedPointer(PointerBuffer pDevPtr, PointerBuffer pSize, long resource)	Get a device pointer through which to access a mapped graphics resource.
static int	cuGraphicsResourceSetMapFlags(long resource, int flags)	Set usage flags for mapping a graphics resource.
static int	cuGraphicsSubResourceGetMappedArray(PointerBuffer pArray, long resource, int arrayIndex, int mipLevel)	Get an array through which to access a subresource of a mapped graphics resource.
static int	cuGraphicsUnmapResources(PointerBuffer resources, long hStream)	Unmap graphics resources.
static int	cuGraphicsUnregisterResource(long resource)	Unregisters a graphics resource for access by CUDA.
static int	cuGraphInstantiate(PointerBuffer phGraphExec, long hGraph, PointerBuffer phErrorNode, ByteBuffer logBuffer)	Creates an executable graph from a graph.
static int	cuGraphInstantiateWithFlags(PointerBuffer phGraphExec, long hGraph, long flags)	Creates an executable graph from a graph.
static int	cuGraphKernelNodeCopyAttributes(long dst, long src)	Copies attributes from source node to destination node.
static int	cuGraphKernelNodeGetAttribute(long hNode, int attr, CUkernelNodeAttrValue value_out)	Queries node attribute.
static int	cuGraphKernelNodeGetParams(long hNode, CUDA_KERNEL_NODE_PARAMS nodeParams)	Returns a kernel node's parameters.
static int	cuGraphKernelNodeSetAttribute(long hNode, int attr, CUkernelNodeAttrValue value)	Sets node attribute.
static int	cuGraphKernelNodeSetParams(long hNode, CUDA_KERNEL_NODE_PARAMS nodeParams)	Sets a kernel node's parameters.
static int	cuGraphLaunch(long hGraphExec, long hStream)	Launches an executable graph in a stream.
static int	cuGraphMemAllocNodeGetParams(long hNode, CUDA_MEM_ALLOC_NODE_PARAMS params_out)	Returns a memory alloc node's parameters.
static int	cuGraphMemcpyNodeGetParams(long hNode, CUDA_MEMCPY3D nodeParams)	Returns a memcpy node's parameters.
static int	cuGraphMemcpyNodeSetParams(long hNode, CUDA_MEMCPY3D nodeParams)	Sets a memcpy node's parameters.
static int	cuGraphMemFreeNodeGetParams(long hNode, PointerBuffer dptr_out)	Returns a memory free node's parameters.
static int	cuGraphMemsetNodeGetParams(long hNode, CUDA_MEMSET_NODE_PARAMS nodeParams)	Returns a memset node's parameters.
static int	cuGraphMemsetNodeSetParams(long hNode, CUDA_MEMSET_NODE_PARAMS nodeParams)	Sets a memset node's parameters.
static int	cuGraphNodeFindInClone(PointerBuffer phNode, long hOriginalNode, long hClonedGraph)	Finds a cloned version of a node.
static int	cuGraphNodeGetDependencies(long hNode, PointerBuffer dependencies, PointerBuffer numDependencies)	Returns a node's dependencies.
static int	cuGraphNodeGetDependentNodes(long hNode, PointerBuffer dependentNodes, PointerBuffer numDependentNodes)	Returns a node's dependent nodes.
static int	cuGraphNodeGetType(long hNode, IntBuffer type)	Returns a node's type.
static int	cuGraphReleaseUserObject(long graph, long object, int count)	Release a user object reference from a graph.
static int	cuGraphRemoveDependencies(long hGraph, PointerBuffer from, PointerBuffer to)	Removes dependency edges from a graph.
static int	cuGraphRetainUserObject(long graph, long object, int count, int flags)	Retain a reference to a user object from a graph.
static int	cuGraphUpload(long hGraphExec, long hStream)	Uploads an executable graph in a stream.
static int	cuImportExternalMemory(PointerBuffer extMem_out, CUDA_EXTERNAL_MEMORY_HANDLE_DESC memHandleDesc)	Imports an external memory object.
static int	cuImportExternalSemaphore(PointerBuffer extSem_out, CUDA_EXTERNAL_SEMAPHORE_HANDLE_DESC semHandleDesc)	Imports an external semaphore.
static int	cuInit(int Flags)	Initialize the CUDA driver API.
static int	cuIpcCloseMemHandle(long dptr)	Attempts to close memory mapped with IpcOpenMemHandle.
static int	cuIpcGetEventHandle(CUIPCEventHandle pHandle, long event)	Gets an interprocess handle for a previously allocated event.
static int	cuIpcGetMemHandle(CUIPCMemHandle pHandle, long dptr)	Gets an interprocess memory handle for an existing device memory allocation.
static int	cuIpcOpenEventHandle(PointerBuffer phEvent, CUIPCEventHandle handle)	Opens an interprocess event handle for use in the current process.
static int	cuIpcOpenMemHandle(PointerBuffer pdptr, CUIPCMemHandle handle, int Flags)	Opens an interprocess memory handle exported from another process and returns a device pointer usable in the local process.
static int	cuLaunch(long f)	Launches a CUDA function.
static int	cuLaunchCooperativeKernel(long f, int gridDimX, int gridDimY, int gridDimZ, int blockDimX, int blockDimY, int blockDimZ, int sharedMemBytes, long hStream, PointerBuffer kernelParams)	Launches a CUDA function where thread blocks can cooperate and synchronize as they execute.
static int	cuLaunchCooperativeKernelMultiDevice(CUDA_LAUNCH_PARAMS.Buffer launchParamsList, int flags)	Launches CUDA functions on multiple devices where thread blocks can cooperate and synchronize as they executeDeprecated: This function is deprecated as of CUDA 11.3.
static int	cuLaunchGrid(long f, int grid_width, int grid_height)	Launches a CUDA function.
static int	cuLaunchGridAsync(long f, int grid_width, int grid_height, long hStream)	Launches a CUDA function.
static int	cuLaunchHostFunc(long hStream, CUhostFnI fn, long userData)	Enqueues a host function call in a stream.
static int	cuLaunchKernel(long f, int gridDimX, int gridDimY, int gridDimZ, int blockDimX, int blockDimY, int blockDimZ, int sharedMemBytes, long hStream, PointerBuffer kernelParams, PointerBuffer extra)	Launches a CUDA function.
static int	cuLinkAddData(long state, int type, ByteBuffer data, CharSequence name, IntBuffer options, PointerBuffer optionValues)	Add an input to a pending linker invocation.
static int	cuLinkAddData(long state, int type, ByteBuffer data, ByteBuffer name, IntBuffer options, PointerBuffer optionValues)	Add an input to a pending linker invocation.
static int	cuLinkAddFile(long state, int type, CharSequence path, IntBuffer options, PointerBuffer optionValues)	Add a file input to a pending linker invocation.
static int	cuLinkAddFile(long state, int type, ByteBuffer path, IntBuffer options, PointerBuffer optionValues)	Add a file input to a pending linker invocation.
static int	cuLinkComplete(long state, PointerBuffer cubinOut, PointerBuffer sizeOut)	Complete a pending linker invocation.
static int	cuLinkCreate(IntBuffer options, PointerBuffer optionValues, PointerBuffer stateOut)	Creates a pending JIT linker invocation.
static int	cuLinkDestroy(long state)	Destroys state for a JIT linker invocation.
static int	cuMemAddressFree(long ptr, long size)	Free an address range reservation.
static int	cuMemAddressReserve(PointerBuffer ptr, long size, long alignment, long addr, long flags)	Allocate an address range reservation.
static int	cuMemAdvise(long devPtr, long count, int advice, int device)	Advise about the usage of a given memory range.
static int	cuMemAlloc(PointerBuffer dptr, long bytesize)	Allocates device memory.
static int	cuMemAllocAsync(PointerBuffer dptr, long bytesize, long hStream)	Allocates memory with stream ordered semantics
static int	cuMemAllocFromPoolAsync(PointerBuffer dptr, long bytesize, long pool, long hStream)	Allocates memory from a specified pool with stream ordered semantics.
static int	cuMemAllocHost(PointerBuffer pp, long bytesize)	Allocates page-locked host memory.
static int	cuMemAllocManaged(PointerBuffer dptr, long bytesize, int flags)	Allocates memory that will be automatically managed by the Unified Memory system.
static int	cuMemAllocPitch(PointerBuffer dptr, PointerBuffer pPitch, long WidthInBytes, long Height, int ElementSizeBytes)	Allocates pitched device memory.
static int	cuMemcpy(long dst, long src, long ByteCount)	Copies memory.
static int	cuMemcpy2D(CUDA_MEMCPY2D pCopy)	Copies memory for 2D arrays.
static int	cuMemcpy2DAsync(CUDA_MEMCPY2D pCopy, long hStream)	Copies memory for 2D arrays.
static int	cuMemcpy2DUnaligned(CUDA_MEMCPY2D pCopy)	Copies memory for 2D arrays.
static int	cuMemcpy3D(CUDA_MEMCPY3D pCopy)	Copies memory for 3D arrays.
static int	cuMemcpy3DAsync(CUDA_MEMCPY3D pCopy, long hStream)	Copies memory for 3D arrays.
static int	cuMemcpy3DPeer(CUDA_MEMCPY3D_PEER pCopy)	Copies memory between contexts.
static int	cuMemcpy3DPeerAsync(CUDA_MEMCPY3D_PEER pCopy, long hStream)	Copies memory between contexts asynchronously.
static int	cuMemcpyAsync(long dst, long src, long ByteCount, long hStream)	Copies memory asynchronously.
static int	cuMemcpyAtoA(long dstArray, long dstOffset, long srcArray, long srcOffset, long ByteCount)	Copies memory from Array to Array.
static int	cuMemcpyAtoD(long dstDevice, long srcArray, long srcOffset, long ByteCount)	Copies memory from Array to Device.
static int	cuMemcpyAtoH(ByteBuffer dstHost, long srcArray, long srcOffset)	Copies memory from Array to Host.
static int	cuMemcpyAtoH(DoubleBuffer dstHost, long srcArray, long srcOffset)	Copies memory from Array to Host.
static int	cuMemcpyAtoH(FloatBuffer dstHost, long srcArray, long srcOffset)	Copies memory from Array to Host.
static int	cuMemcpyAtoH(IntBuffer dstHost, long srcArray, long srcOffset)	Copies memory from Array to Host.
static int	cuMemcpyAtoH(LongBuffer dstHost, long srcArray, long srcOffset)	Copies memory from Array to Host.
static int	cuMemcpyAtoH(ShortBuffer dstHost, long srcArray, long srcOffset)	Copies memory from Array to Host.
static int	cuMemcpyAtoH(PointerBuffer dstHost, long srcArray, long srcOffset)	Copies memory from Array to Host.
static int	cuMemcpyAtoHAsync(ByteBuffer dstHost, long srcArray, long srcOffset, long hStream)	Copies memory from Array to Host.
static int	cuMemcpyAtoHAsync(DoubleBuffer dstHost, long srcArray, long srcOffset, long hStream)	Copies memory from Array to Host.
static int	cuMemcpyAtoHAsync(FloatBuffer dstHost, long srcArray, long srcOffset, long hStream)	Copies memory from Array to Host.
static int	cuMemcpyAtoHAsync(IntBuffer dstHost, long srcArray, long srcOffset, long hStream)	Copies memory from Array to Host.
static int	cuMemcpyAtoHAsync(LongBuffer dstHost, long srcArray, long srcOffset, long hStream)	Copies memory from Array to Host.
static int	cuMemcpyAtoHAsync(ShortBuffer dstHost, long srcArray, long srcOffset, long hStream)	Copies memory from Array to Host.
static int	cuMemcpyAtoHAsync(PointerBuffer dstHost, long srcArray, long srcOffset, long hStream)	Copies memory from Array to Host.
static int	cuMemcpyDtoA(long dstArray, long dstOffset, long srcDevice, long ByteCount)	Copies memory from Device to Array.
static int	cuMemcpyDtoD(long dstDevice, long srcDevice, long ByteCount)	Copies memory from Device to Device.
static int	cuMemcpyDtoDAsync(long dstDevice, long srcDevice, long ByteCount, long hStream)	Copies memory from Device to Device.
static int	cuMemcpyDtoH(ByteBuffer dstHost, long srcDevice)	Copies memory from Device to Host.
static int	cuMemcpyDtoH(DoubleBuffer dstHost, long srcDevice)	Copies memory from Device to Host.
static int	cuMemcpyDtoH(FloatBuffer dstHost, long srcDevice)	Copies memory from Device to Host.
static int	cuMemcpyDtoH(IntBuffer dstHost, long srcDevice)	Copies memory from Device to Host.
static int	cuMemcpyDtoH(LongBuffer dstHost, long srcDevice)	Copies memory from Device to Host.
static int	cuMemcpyDtoH(ShortBuffer dstHost, long srcDevice)	Copies memory from Device to Host.
static int	cuMemcpyDtoH(PointerBuffer dstHost, long srcDevice)	Copies memory from Device to Host.
static int	cuMemcpyDtoHAsync(ByteBuffer dstHost, long srcDevice, long hStream)	Copies memory from Device to Host.
static int	cuMemcpyDtoHAsync(DoubleBuffer dstHost, long srcDevice, long hStream)	Copies memory from Device to Host.
static int	cuMemcpyDtoHAsync(FloatBuffer dstHost, long srcDevice, long hStream)	Copies memory from Device to Host.
static int	cuMemcpyDtoHAsync(IntBuffer dstHost, long srcDevice, long hStream)	Copies memory from Device to Host.
static int	cuMemcpyDtoHAsync(LongBuffer dstHost, long srcDevice, long hStream)	Copies memory from Device to Host.
static int	cuMemcpyDtoHAsync(ShortBuffer dstHost, long srcDevice, long hStream)	Copies memory from Device to Host.
static int	cuMemcpyDtoHAsync(PointerBuffer dstHost, long srcDevice, long hStream)	Copies memory from Device to Host.
static int	cuMemcpyHtoA(long dstArray, long dstOffset, ByteBuffer srcHost)	Copies memory from Host to Array.
static int	cuMemcpyHtoA(long dstArray, long dstOffset, DoubleBuffer srcHost)	Copies memory from Host to Array.
static int	cuMemcpyHtoA(long dstArray, long dstOffset, FloatBuffer srcHost)	Copies memory from Host to Array.
static int	cuMemcpyHtoA(long dstArray, long dstOffset, IntBuffer srcHost)	Copies memory from Host to Array.
static int	cuMemcpyHtoA(long dstArray, long dstOffset, LongBuffer srcHost)	Copies memory from Host to Array.
static int	cuMemcpyHtoA(long dstArray, long dstOffset, ShortBuffer srcHost)	Copies memory from Host to Array.
static int	cuMemcpyHtoA(long dstArray, long dstOffset, PointerBuffer srcHost)	Copies memory from Host to Array.
static int	cuMemcpyHtoAAsync(long dstArray, long dstOffset, ByteBuffer srcHost, long hStream)	Copies memory from Host to Array.
static int	cuMemcpyHtoAAsync(long dstArray, long dstOffset, DoubleBuffer srcHost, long hStream)	Copies memory from Host to Array.
static int	cuMemcpyHtoAAsync(long dstArray, long dstOffset, FloatBuffer srcHost, long hStream)	Copies memory from Host to Array.
static int	cuMemcpyHtoAAsync(long dstArray, long dstOffset, IntBuffer srcHost, long hStream)	Copies memory from Host to Array.
static int	cuMemcpyHtoAAsync(long dstArray, long dstOffset, LongBuffer srcHost, long hStream)	Copies memory from Host to Array.
static int	cuMemcpyHtoAAsync(long dstArray, long dstOffset, ShortBuffer srcHost, long hStream)	Copies memory from Host to Array.
static int	cuMemcpyHtoAAsync(long dstArray, long dstOffset, PointerBuffer srcHost, long hStream)	Copies memory from Host to Array.
static int	cuMemcpyHtoD(long dstDevice, ByteBuffer srcHost)	Copies memory from Host to Device.
static int	cuMemcpyHtoD(long dstDevice, DoubleBuffer srcHost)	Copies memory from Host to Device.
static int	cuMemcpyHtoD(long dstDevice, FloatBuffer srcHost)	Copies memory from Host to Device.
static int	cuMemcpyHtoD(long dstDevice, IntBuffer srcHost)	Copies memory from Host to Device.
static int	cuMemcpyHtoD(long dstDevice, LongBuffer srcHost)	Copies memory from Host to Device.
static int	cuMemcpyHtoD(long dstDevice, ShortBuffer srcHost)	Copies memory from Host to Device.
static int	cuMemcpyHtoD(long dstDevice, PointerBuffer srcHost)	Copies memory from Host to Device.
static int	cuMemcpyHtoDAsync(long dstDevice, ByteBuffer srcHost, long hStream)	Copies memory from Host to Device.
static int	cuMemcpyHtoDAsync(long dstDevice, DoubleBuffer srcHost, long hStream)	Copies memory from Host to Device.
static int	cuMemcpyHtoDAsync(long dstDevice, FloatBuffer srcHost, long hStream)	Copies memory from Host to Device.
static int	cuMemcpyHtoDAsync(long dstDevice, IntBuffer srcHost, long hStream)	Copies memory from Host to Device.
static int	cuMemcpyHtoDAsync(long dstDevice, LongBuffer srcHost, long hStream)	Copies memory from Host to Device.
static int	cuMemcpyHtoDAsync(long dstDevice, ShortBuffer srcHost, long hStream)	Copies memory from Host to Device.
static int	cuMemcpyHtoDAsync(long dstDevice, PointerBuffer srcHost, long hStream)	Copies memory from Host to Device.
static int	cuMemcpyPeer(long dstDevice, long dstContext, long srcDevice, long srcContext, long ByteCount)	Copies device memory between two contexts.
static int	cuMemcpyPeerAsync(long dstDevice, long dstContext, long srcDevice, long srcContext, long ByteCount, long hStream)	Copies device memory between two contexts asynchronously.
static int	cuMemCreate(LongBuffer handle, long size, CUmemAllocationProp prop, long flags)	Create a CUDA memory handle representing a memory allocation of a given size described by the given properties.
static int	cuMemExportToShareableHandle(ByteBuffer shareableHandle, long handle, int handleType, long flags)	Exports an allocation to a requested shareable handle type.
static int	cuMemExportToShareableHandle(PointerBuffer shareableHandle, long handle, int handleType, long flags)	Exports an allocation to a requested shareable handle type.
static int	cuMemFree(long dptr)	Frees device memory.
static int	cuMemFreeAsync(long dptr, long hStream)	Frees memory with stream ordered semantics.
static int	cuMemFreeHost(ByteBuffer p)	Frees page-locked host memory.
static int	cuMemGetAccess(LongBuffer flags, CUmemLocation location, long ptr)	Get the access flags set for the given location and ptr.
static int	cuMemGetAddressRange(PointerBuffer pbase, PointerBuffer psize, long dptr)	Get information on memory allocations.
static int	cuMemGetAllocationGranularity(PointerBuffer granularity, CUmemAllocationProp prop, int option)	Calculates either the minimal or recommended granularity.
static int	cuMemGetAllocationPropertiesFromHandle(CUmemAllocationProp prop, long handle)	Retrieve the contents of the property structure defining properties for this handle.
static int	cuMemGetInfo(PointerBuffer free, PointerBuffer total)	Gets free and total memory.
static int	cuMemHostAlloc(PointerBuffer pp, long bytesize, int Flags)	Allocates page-locked host memory.
static int	cuMemHostGetDevicePointer(PointerBuffer pdptr, ByteBuffer p, int Flags)	Passes back device pointer of mapped pinned memory.
static int	cuMemHostGetFlags(IntBuffer pFlags, ByteBuffer p)	Passes back flags that were used for a pinned allocation
static int	cuMemHostRegister(ByteBuffer p, int Flags)	Registers an existing host memory range for use by CUDA.
static int	cuMemHostUnregister(ByteBuffer p)	Unregisters a memory range that was registered with MemHostRegister.
static int	cuMemImportFromShareableHandle(LongBuffer handle, long osHandle, int shHandleType)	Imports an allocation from a requested shareable handle type.
static int	cuMemMap(long ptr, long size, long offset, long handle, long flags)	Maps an allocation handle to a reserved virtual address range.
static int	cuMemMapArrayAsync(CUarrayMapInfo.Buffer mapInfoList, long hStream)	Maps or unmaps subregions of sparse CUDA arrays and sparse CUDA mipmapped arrays.
static int	cuMemPoolCreate(PointerBuffer pool, CUmemPoolProps poolProps)	Creates a memory pool.
static int	cuMemPoolDestroy(long pool)	Destroys the specified memory pool.
static int	cuMemPoolExportPointer(CUmemPoolPtrExportData shareData_out, long ptr)	Export data to share a memory pool allocation between processes.
static int	cuMemPoolExportToShareableHandle(ByteBuffer handle_out, long pool, int handleType, long flags)	Exports a memory pool to the requested handle type.
static int	cuMemPoolExportToShareableHandle(PointerBuffer handle_out, long pool, int handleType, long flags)	Exports a memory pool to the requested handle type.
static int	cuMemPoolGetAccess(IntBuffer flags, long memPool, CUmemLocation location)	Returns the accessibility of a pool from a device.
static int	cuMemPoolGetAttribute(long pool, int attr, ByteBuffer value)	Gets attributes of a memory pool.
static int	cuMemPoolGetAttribute(long pool, int attr, IntBuffer value)	Gets attributes of a memory pool.
static int	cuMemPoolGetAttribute(long pool, int attr, LongBuffer value)	Gets attributes of a memory pool.
static int	cuMemPoolImportFromShareableHandle(PointerBuffer pool_out, ByteBuffer handle, int handleType, long flags)	Imports a memory pool from a shared handle.
static int	cuMemPoolImportFromShareableHandle(PointerBuffer pool_out, PointerBuffer handle, int handleType, long flags)	Imports a memory pool from a shared handle.
static int	cuMemPoolImportPointer(PointerBuffer ptr_out, long pool, CUmemPoolPtrExportData shareData)	Import a memory pool allocation from another process.
static int	cuMemPoolSetAccess(long pool, CUmemAccessDesc.Buffer map)	Controls visibility of pools between devices.
static int	cuMemPoolSetAttribute(long pool, int attr, ByteBuffer value)	Sets attributes of a memory pool.
static int	cuMemPoolSetAttribute(long pool, int attr, IntBuffer value)	Sets attributes of a memory pool.
static int	cuMemPoolSetAttribute(long pool, int attr, LongBuffer value)	Sets attributes of a memory pool.
static int	cuMemPoolTrimTo(long pool, long minBytesToKeep)	Tries to release memory back to the OS.
static int	cuMemPrefetchAsync(long devPtr, long count, int dstDevice, long hStream)	Prefetches memory to the specified destination device,
static int	cuMemRangeGetAttribute(ByteBuffer data, int attribute, long devPtr, long count)	Query an attribute of a given memory range.
static int	cuMemRangeGetAttributes(PointerBuffer data, PointerBuffer dataSizes, IntBuffer attributes, long devPtr, long count)	Query attributes of a given memory range.
static int	cuMemRelease(long handle)	Release a memory handle representing a memory allocation which was previously allocated through MemCreate.
static int	cuMemRetainAllocationHandle(LongBuffer handle, ByteBuffer addr)	Given an address addr, returns the allocation handle of the backing memory allocation.
static int	cuMemSetAccess(long ptr, long size, CUmemAccessDesc.Buffer desc)	Set the access flags for each location specified in desc for the given virtual address range.
static int	cuMemsetD16(long dstDevice, short us, long N)	Initializes device memory.
static int	cuMemsetD16Async(long dstDevice, short us, long N, long hStream)	Sets device memory
static int	cuMemsetD2D16(long dstDevice, long dstPitch, short us, long Width, long Height)	Initializes device memory.
static int	cuMemsetD2D16Async(long dstDevice, long dstPitch, short us, long Width, long Height, long hStream)	Sets device memory.
static int	cuMemsetD2D32(long dstDevice, long dstPitch, int ui, long Width, long Height)	Initializes device memory.
static int	cuMemsetD2D32Async(long dstDevice, long dstPitch, int ui, long Width, long Height, long hStream)	Sets device memory.
static int	cuMemsetD2D8(long dstDevice, long dstPitch, byte uc, long Width, long Height)	Initializes device memory.
static int	cuMemsetD2D8Async(long dstDevice, long dstPitch, byte uc, long Width, long Height, long hStream)	Sets device memory.
static int	cuMemsetD32(long dstDevice, int ui, long N)	Initializes device memory
static int	cuMemsetD32Async(long dstDevice, int ui, long N, long hStream)	Sets device memory.
static int	cuMemsetD8(long dstDevice, byte uc, long N)	Initializes device memory.
static int	cuMemsetD8Async(long dstDevice, byte uc, long N, long hStream)	Sets device memory
static int	cuMemUnmap(long ptr, long size)	Unmap the backing memory of a given address range.
static int	cuMipmappedArrayCreate(PointerBuffer pHandle, CUDA_ARRAY3D_DESCRIPTOR pMipmappedArrayDesc, int numMipmapLevels)	Creates a CUDA mipmapped array.
static int	cuMipmappedArrayDestroy(long hMipmappedArray)	Destroys a CUDA mipmapped array.
static int	cuMipmappedArrayGetLevel(PointerBuffer pLevelArray, long hMipmappedArray, int level)	Gets a mipmap level of a CUDA mipmapped array.
static int	cuMipmappedArrayGetSparseProperties(CUDA_ARRAY_SPARSE_PROPERTIES sparseProperties, long mipmap)	Returns the layout properties of a sparse CUDA mipmapped array.
static int	cuModuleGetFunction(PointerBuffer hfunc, long hmod, CharSequence name)	Returns a function handle.
static int	cuModuleGetFunction(PointerBuffer hfunc, long hmod, ByteBuffer name)	Returns a function handle.
static int	cuModuleGetGlobal(PointerBuffer dptr, PointerBuffer bytes, long hmod, CharSequence name)	Returns a global pointer from a module.
static int	cuModuleGetGlobal(PointerBuffer dptr, PointerBuffer bytes, long hmod, ByteBuffer name)	Returns a global pointer from a module.
static int	cuModuleGetSurfRef(PointerBuffer pSurfRef, long hmod, CharSequence name)	Returns a handle to a surface reference.
static int	cuModuleGetSurfRef(PointerBuffer pSurfRef, long hmod, ByteBuffer name)	Returns a handle to a surface reference.
static int	cuModuleGetTexRef(PointerBuffer pTexRef, long hmod, CharSequence name)	Returns a handle to a texture reference.
static int	cuModuleGetTexRef(PointerBuffer pTexRef, long hmod, ByteBuffer name)	Returns a handle to a texture reference.
static int	cuModuleLoad(PointerBuffer module, CharSequence fname)	Loads a compute module.
static int	cuModuleLoad(PointerBuffer module, ByteBuffer fname)	Loads a compute module.
static int	cuModuleLoadData(PointerBuffer module, ByteBuffer image)	Load a module's data.
static int	cuModuleLoadDataEx(PointerBuffer module, ByteBuffer image, IntBuffer options, PointerBuffer optionValues)	Load a module's data with options.
static int	cuModuleLoadFatBinary(PointerBuffer module, ByteBuffer fatCubin)	Load a module's data.
static int	cuModuleUnload(long hmod)	Unloads a module.
static int	cuOccupancyAvailableDynamicSMemPerBlock(PointerBuffer dynamicSmemSize, long func, int numBlocks, int blockSize)	Returns dynamic shared memory available per block when launching numBlocks blocks on SM.
static int	cuOccupancyMaxActiveBlocksPerMultiprocessor(IntBuffer numBlocks, long func, int blockSize, long dynamicSMemSize)	Returns occupancy of a function.
static int	cuOccupancyMaxActiveBlocksPerMultiprocessorWithFlags(IntBuffer numBlocks, long func, int blockSize, long dynamicSMemSize, int flags)	Returns occupancy of a function.
static int	cuOccupancyMaxPotentialBlockSize(IntBuffer minGridSize, IntBuffer blockSize, long func, CUoccupancyB2DSizeI blockSizeToDynamicSMemSize, long dynamicSMemSize, int blockSizeLimit)	Suggest a launch configuration with reasonable occupancy.
static int	cuOccupancyMaxPotentialBlockSizeWithFlags(IntBuffer minGridSize, IntBuffer blockSize, long func, CUoccupancyB2DSizeI blockSizeToDynamicSMemSize, long dynamicSMemSize, int blockSizeLimit, int flags)	Suggest a launch configuration with reasonable occupancy.
static int	cuParamSetf(long hfunc, int offset, float value)	Adds a floating-point parameter to the function's argument list.
static int	cuParamSeti(long hfunc, int offset, int value)	Adds an integer parameter to the function's argument listDeprecated:
static int	cuParamSetSize(long hfunc, int numbytes)	Sets the parameter size for the function.
static int	cuParamSetTexRef(long hfunc, int texunit, long hTexRef)	Adds a texture-reference to the function's argument list.
static int	cuParamSetv(long hfunc, int offset, ByteBuffer ptr)	Adds arbitrary data to the function's argument list.
static int	cuPointerGetAttribute(ByteBuffer data, int attribute, long ptr)	Returns information about a pointer.
static int	cuPointerGetAttribute(IntBuffer data, int attribute, long ptr)	Returns information about a pointer.
static int	cuPointerGetAttribute(LongBuffer data, int attribute, long ptr)	Returns information about a pointer.
static int	cuPointerGetAttribute(PointerBuffer data, int attribute, long ptr)	Returns information about a pointer.
static int	cuPointerGetAttributes(IntBuffer attributes, PointerBuffer data, long ptr)	Returns information about a pointer.
static int	cuPointerSetAttribute(ByteBuffer value, int attribute, long ptr)	Set attributes on a previously allocated memory region.
static int	cuSignalExternalSemaphoresAsync(PointerBuffer extSemArray, CUDA_EXTERNAL_SEMAPHORE_SIGNAL_PARAMS.Buffer paramsArray, long stream)	Signals a set of external semaphore objects,
static int	cuStreamAddCallback(long hStream, CUstreamCallbackI callback, long userData, int flags)	Add a callback to a compute stream.
static int	cuStreamAttachMemAsync(long hStream, long dptr, long length, int flags)	Attach memory to a stream asynchronously.
static int	cuStreamBatchMemOp(long stream, CUstreamBatchMemOpParams.Buffer paramArray, int flags)	Batch operations to synchronize the stream via memory operations.
static int	cuStreamBeginCapture(long hStream)	Begins graph capture on a stream.
static int	cuStreamBeginCapture_v2(long hStream, int mode)	Begins graph capture on a stream.
static int	cuStreamCopyAttributes(long dst, long src)	Copies attributes from source stream to destination stream.
static int	cuStreamCreate(PointerBuffer phStream, int Flags)	Create a stream.
static int	cuStreamCreateWithPriority(PointerBuffer phStream, int flags, int priority)	Create a stream with the given priority.
static int	cuStreamDestroy(long hStream)	Destroys a stream.
static int	cuStreamEndCapture(long hStream, PointerBuffer phGraph)	Ends capture on a stream, returning the captured graph.
static int	cuStreamGetAttribute(long hStream, int attr, CUstreamAttrValue value_out)	Queries stream attribute.
static int	cuStreamGetCaptureInfo(long hStream, IntBuffer captureStatus, LongBuffer id)	Query capture status of a stream.
static int	cuStreamGetCaptureInfo_v2(long hStream, IntBuffer captureStatus_out, LongBuffer id_out, PointerBuffer graph_out, PointerBuffer dependencies_out, PointerBuffer numDependencies_out)	Query a stream's capture state (11.3+).
static int	cuStreamGetCtx(long hStream, PointerBuffer pctx)	Query the context associated with a stream.
static int	cuStreamGetFlags(long hStream, IntBuffer flags)	Query the flags of a given stream.
static int	cuStreamGetPriority(long hStream, IntBuffer priority)	Query the priority of a given stream.
static int	cuStreamIsCapturing(long hStream, IntBuffer captureStatus)	Returns a stream's capture status.
static int	cuStreamQuery(long hStream)	Determine status of a compute stream.
static int	cuStreamSetAttribute(long hStream, int attr, CUstreamAttrValue value)	Sets stream attribute.
static int	cuStreamSynchronize(long hStream)	Wait until a stream's tasks are completed.
static int	cuStreamUpdateCaptureDependencies(long hStream, PointerBuffer dependencies, int flags)	Update the set of dependencies in a capturing stream (11.3+).
static int	cuStreamWaitEvent(long hStream, long hEvent, int Flags)	Make a compute stream wait on an event.
static int	cuStreamWaitValue32(long stream, long addr, int value, int flags)	Wait on a memory location.
static int	cuStreamWaitValue64(long stream, long addr, long value, int flags)	Wait on a memory location.
static int	cuStreamWriteValue32(long stream, long addr, int value, int flags)	Write a value to memory.
static int	cuStreamWriteValue64(long stream, long addr, long value, int flags)	Write a value to memory.
static int	cuSurfObjectCreate(LongBuffer pSurfObject, CUDA_RESOURCE_DESC pResDesc)	Creates a surface object.
static int	cuSurfObjectDestroy(long surfObject)	Destroys a surface object.
static int	cuSurfObjectGetResourceDesc(CUDA_RESOURCE_DESC pResDesc, long surfObject)	Returns a surface object's resource descriptor.
static int	cuSurfRefGetArray(PointerBuffer phArray, long hSurfRef)	Passes back the CUDA array bound to a surface reference.
static int	cuSurfRefSetArray(long hSurfRef, long hArray, int Flags)	Sets the CUDA array for a surface reference.Deprecated:
static int	cuTexObjectCreate(LongBuffer pTexObject, CUDA_RESOURCE_DESC pResDesc, CUDA_TEXTURE_DESC pTexDesc, CUDA_RESOURCE_VIEW_DESC pResViewDesc)	Creates a texture object.
static int	cuTexObjectDestroy(long texObject)	Destroys a texture object.
static int	cuTexObjectGetResourceDesc(CUDA_RESOURCE_DESC pResDesc, long texObject)	Returns a texture object's resource descriptor.
static int	cuTexObjectGetResourceViewDesc(CUDA_RESOURCE_VIEW_DESC pResViewDesc, long texObject)	Returns a texture object's resource view descriptor.
static int	cuTexObjectGetTextureDesc(CUDA_TEXTURE_DESC pTexDesc, long texObject)	Returns a texture object's texture descriptor.
static int	cuTexRefCreate(PointerBuffer pTexRef)	Creates a texture reference.
static int	cuTexRefDestroy(long hTexRef)	Destroys a texture reference.
static int	cuTexRefGetAddress(PointerBuffer pdptr, long hTexRef)	Gets the address associated with a texture reference.
static int	cuTexRefGetAddressMode(IntBuffer pam, long hTexRef, int dim)	Gets the addressing mode used by a texture reference.
static int	cuTexRefGetArray(PointerBuffer phArray, long hTexRef)	Gets the array bound to a texture reference.
static int	cuTexRefGetBorderColor(FloatBuffer pBorderColor, long hTexRef)	Gets the border color used by a texture reference.
static int	cuTexRefGetFilterMode(IntBuffer pfm, long hTexRef)	Gets the filter-mode used by a texture reference.
static int	cuTexRefGetFlags(IntBuffer pFlags, long hTexRef)	Gets the flags used by a texture reference.
static int	cuTexRefGetFormat(IntBuffer pFormat, IntBuffer pNumChannels, long hTexRef)	Gets the format used by a texture reference.
static int	cuTexRefGetMaxAnisotropy(IntBuffer pmaxAniso, long hTexRef)	Gets the maximum anisotropy for a texture reference.
static int	cuTexRefGetMipmapFilterMode(IntBuffer pfm, long hTexRef)	Gets the mipmap filtering mode for a texture reference.
static int	cuTexRefGetMipmapLevelBias(FloatBuffer pbias, long hTexRef)	Gets the mipmap level bias for a texture reference.
static int	cuTexRefGetMipmapLevelClamp(FloatBuffer pminMipmapLevelClamp, FloatBuffer pmaxMipmapLevelClamp, long hTexRef)	Gets the min/max mipmap level clamps for a texture reference.
static int	cuTexRefGetMipmappedArray(PointerBuffer phMipmappedArray, long hTexRef)	Gets the mipmapped array bound to a texture reference.
static int	cuTexRefSetAddress(PointerBuffer ByteOffset, long hTexRef, long dptr, long bytes)	Binds an address as a texture reference.
static int	cuTexRefSetAddress2D(long hTexRef, CUDA_ARRAY_DESCRIPTOR desc, long dptr, long Pitch)	Binds an address as a 2D texture reference.
static int	cuTexRefSetAddressMode(long hTexRef, int dim, int am)	Sets the addressing mode for a texture reference.
static int	cuTexRefSetArray(long hTexRef, long hArray, int Flags)	Binds an array as a texture reference.
static int	cuTexRefSetBorderColor(long hTexRef, FloatBuffer pBorderColor)	Sets the border color for a texture reference.
static int	cuTexRefSetFilterMode(long hTexRef, int fm)	Sets the filtering mode for a texture reference.
static int	cuTexRefSetFlags(long hTexRef, int Flags)	Sets the flags for a texture reference.
static int	cuTexRefSetFormat(long hTexRef, int fmt, int NumPackedComponents)	Sets the format for a texture reference.
static int	cuTexRefSetMaxAnisotropy(long hTexRef, int maxAniso)	Sets the maximum anisotropy for a texture reference.
static int	cuTexRefSetMipmapFilterMode(long hTexRef, int fm)	Sets the mipmap filtering mode for a texture reference (Deprecated)
static int	cuTexRefSetMipmapLevelBias(long hTexRef, float bias)	Sets the mipmap level bias for a texture reference.
static int	cuTexRefSetMipmapLevelClamp(long hTexRef, float minMipmapLevelClamp, float maxMipmapLevelClamp)	Sets the mipmap min/max mipmap level clamps for a texture reference.
static int	cuTexRefSetMipmappedArray(long hTexRef, long hMipmappedArray, int Flags)	Binds a mipmapped array to a texture reference.
static int	cuThreadExchangeStreamCaptureMode(IntBuffer mode)	Swaps the stream capture interaction mode for a thread.
static int	cuUserObjectCreate(PointerBuffer object_out, long ptr, CUhostFnI destroy, int initialRefcount, int flags)	Create a user object.
static int	cuUserObjectRelease(long object, int count)	Release a reference to a user object.
static int	cuUserObjectRetain(long object, int count)	Retain a reference to a user object.
static int	cuWaitExternalSemaphoresAsync(PointerBuffer extSemArray, CUDA_EXTERNAL_SEMAPHORE_WAIT_PARAMS.Buffer paramsArray, long stream)	Waits on a set of external semaphore objects.
static SharedLibrary	getLibrary()	Returns the NVCUDA SharedLibrary.
static int	ncuArray3DCreate(long pHandle, long pAllocateArray)	Unsafe version of: Array3DCreate
static int	ncuArray3DGetDescriptor(long pArrayDescriptor, long hArray)	Unsafe version of: Array3DGetDescriptor
static int	ncuArrayCreate(long pHandle, long pAllocateArray)	Unsafe version of: ArrayCreate
static int	ncuArrayGetDescriptor(long pArrayDescriptor, long hArray)	Unsafe version of: ArrayGetDescriptor
static int	ncuArrayGetPlane(long pPlaneArray, long hArray, int planeIdx)	Unsafe version of: ArrayGetPlane
static int	ncuArrayGetSparseProperties(long sparseProperties, long array)	Unsafe version of: ArrayGetSparseProperties
static int	ncuCtxAttach(long pctx, int flags)	Unsafe version of: CtxAttach
static int	ncuCtxCreate(long pctx, int flags, int dev)	Unsafe version of: CtxCreate
static int	ncuCtxCreate_v3(long pctx, long paramsArray, int numParams, int flags, int dev)	Unsafe version of: CtxCreate_v3
static int	ncuCtxGetApiVersion(long ctx, long version)	Unsafe version of: CtxGetApiVersion
static int	ncuCtxGetCacheConfig(long pconfig)	Unsafe version of: CtxGetCacheConfig
static int	ncuCtxGetCurrent(long pctx)	Unsafe version of: CtxGetCurrent
static int	ncuCtxGetDevice(long device)	Unsafe version of: CtxGetDevice
static int	ncuCtxGetExecAffinity(long pExecAffinity, int type)	Unsafe version of: CtxGetExecAffinity
static int	ncuCtxGetFlags(long flags)	Unsafe version of: CtxGetFlags
static int	ncuCtxGetLimit(long pvalue, int limit)	Unsafe version of: CtxGetLimit
static int	ncuCtxGetSharedMemConfig(long pConfig)	Unsafe version of: CtxGetSharedMemConfig
static int	ncuCtxGetStreamPriorityRange(long leastPriority, long greatestPriority)	Unsafe version of: CtxGetStreamPriorityRange
static int	ncuCtxPopCurrent(long pctx)	Unsafe version of: CtxPopCurrent
static int	ncuDeviceCanAccessPeer(long canAccessPeer, int dev, int peerDev)	Unsafe version of: DeviceCanAccessPeer
static int	ncuDeviceComputeCapability(long major, long minor, int dev)	Unsafe version of: DeviceComputeCapability
static int	ncuDeviceGet(long device, int ordinal)	Unsafe version of: DeviceGet
static int	ncuDeviceGetAttribute(long pi, int attrib, int dev)	Unsafe version of: DeviceGetAttribute
static int	ncuDeviceGetByPCIBusId(long dev, long pciBusId)	Unsafe version of: DeviceGetByPCIBusId
static int	ncuDeviceGetCount(long count)	Unsafe version of: DeviceGetCount
static int	ncuDeviceGetDefaultMemPool(long pool_out, int dev)	Unsafe version of: DeviceGetDefaultMemPool
static int	ncuDeviceGetExecAffinitySupport(long pi, int type, int dev)	Unsafe version of: DeviceGetExecAffinitySupport
static int	ncuDeviceGetGraphMemAttribute(int device, int attr, long value)	Unsafe version of: DeviceGetGraphMemAttribute
static int	ncuDeviceGetLuid(long luid, long deviceNodeMask, int dev)	Unsafe version of: DeviceGetLuid
static int	ncuDeviceGetMemPool(long pool, int dev)	Unsafe version of: DeviceGetMemPool
static int	ncuDeviceGetName(long name, int len, int dev)	Unsafe version of: DeviceGetName
static int	ncuDeviceGetNvSciSyncAttributes(long nvSciSyncAttrList, int dev, int flags)	Unsafe version of: DeviceGetNvSciSyncAttributes
static int	ncuDeviceGetP2PAttribute(long value, int attrib, int srcDevice, int dstDevice)	Unsafe version of: DeviceGetP2PAttribute
static int	ncuDeviceGetPCIBusId(long pciBusId, int len, int dev)	Unsafe version of: DeviceGetPCIBusId
static int	ncuDeviceGetProperties(long prop, int dev)	Unsafe version of: DeviceGetProperties
static int	ncuDeviceGetTexture1DLinearMaxWidth(long maxWidthInElements, int format, int numChannels, int dev)	Unsafe version of: DeviceGetTexture1DLinearMaxWidth
static int	ncuDeviceGetUuid(long uuid, int dev)	Unsafe version of: DeviceGetUuid
static int	ncuDeviceGetUuid_v2(long uuid, int dev)	Unsafe version of: DeviceGetUuid_v2
static int	ncuDevicePrimaryCtxGetState(int dev, long flags, long active)	Unsafe version of: DevicePrimaryCtxGetState
static int	ncuDevicePrimaryCtxRetain(long pctx, int dev)	Unsafe version of: DevicePrimaryCtxRetain
static int	ncuDeviceSetGraphMemAttribute(int device, int attr, long value)	Unsafe version of: DeviceSetGraphMemAttribute
static int	ncuDeviceTotalMem(long bytes, int dev)	Unsafe version of: DeviceTotalMem
static int	ncuDriverGetVersion(long driverVersion)	Unsafe version of: DriverGetVersion
static int	ncuEventCreate(long phEvent, int Flags)	Unsafe version of: EventCreate
static int	ncuEventElapsedTime(long pMilliseconds, long hStart, long hEnd)	Unsafe version of: EventElapsedTime
static int	ncuExternalMemoryGetMappedBuffer(long devPtr, long extMem, long bufferDesc)	Unsafe version of: ExternalMemoryGetMappedBuffer
static int	ncuExternalMemoryGetMappedMipmappedArray(long mipmap, long extMem, long mipmapDesc)	Unsafe version of: ExternalMemoryGetMappedMipmappedArray
static int	ncuFuncGetAttribute(long pi, int attrib, long hfunc)	Unsafe version of: FuncGetAttribute
static int	ncuFuncGetModule(long hmod, long hfunc)	Unsafe version of: FuncGetModule
static int	ncuGetErrorName(int error, long pStr)	Unsafe version of: GetErrorName
static int	ncuGetErrorString(int error, long pStr)	Unsafe version of: GetErrorString
static int	ncuGetExportTable(long ppExportTable, long pExportTableId)
static int	ncuGetProcAddress(long symbol, long pfn, int cudaVersion, long flags)	Unsafe version of: GetProcAddress
static int	ncuGraphAddChildGraphNode(long phGraphNode, long hGraph, long dependencies, long numDependencies, long childGraph)	Unsafe version of: GraphAddChildGraphNode
static int	ncuGraphAddDependencies(long hGraph, long from, long to, long numDependencies)	Unsafe version of: GraphAddDependencies
static int	ncuGraphAddEmptyNode(long phGraphNode, long hGraph, long dependencies, long numDependencies)	Unsafe version of: GraphAddEmptyNode
static int	ncuGraphAddEventRecordNode(long phGraphNode, long hGraph, long dependencies, long numDependencies, long event)	Unsafe version of: GraphAddEventRecordNode
static int	ncuGraphAddEventWaitNode(long phGraphNode, long hGraph, long dependencies, long numDependencies, long event)	Unsafe version of: GraphAddEventWaitNode
static int	ncuGraphAddExternalSemaphoresSignalNode(long phGraphNode, long hGraph, long dependencies, long numDependencies, long nodeParams)	Unsafe version of: GraphAddExternalSemaphoresSignalNode
static int	ncuGraphAddExternalSemaphoresWaitNode(long phGraphNode, long hGraph, long dependencies, long numDependencies, long nodeParams)	Unsafe version of: GraphAddExternalSemaphoresWaitNode
static int	ncuGraphAddHostNode(long phGraphNode, long hGraph, long dependencies, long numDependencies, long nodeParams)	Unsafe version of: GraphAddHostNode
static int	ncuGraphAddKernelNode(long phGraphNode, long hGraph, long dependencies, long numDependencies, long nodeParams)	Unsafe version of: GraphAddKernelNode
static int	ncuGraphAddMemAllocNode(long phGraphNode, long hGraph, long dependencies, long numDependencies, long nodeParams)	Unsafe version of: GraphAddMemAllocNode
static int	ncuGraphAddMemcpyNode(long phGraphNode, long hGraph, long dependencies, long numDependencies, long copyParams, long ctx)	Unsafe version of: GraphAddMemcpyNode
static int	ncuGraphAddMemFreeNode(long phGraphNode, long hGraph, long dependencies, long numDependencies, long dptr)	Unsafe version of: GraphAddMemFreeNode
static int	ncuGraphAddMemsetNode(long phGraphNode, long hGraph, long dependencies, long numDependencies, long memsetParams, long ctx)	Unsafe version of: GraphAddMemsetNode
static int	ncuGraphChildGraphNodeGetGraph(long hNode, long phGraph)	Unsafe version of: GraphChildGraphNodeGetGraph
static int	ncuGraphClone(long phGraphClone, long originalGraph)	Unsafe version of: GraphClone
static int	ncuGraphCreate(long phGraph, int flags)	Unsafe version of: GraphCreate
static int	ncuGraphDebugDotPrint(long hGraph, long path, int flags)	Unsafe version of: GraphDebugDotPrint
static int	ncuGraphEventRecordNodeGetEvent(long hNode, long event_out)	Unsafe version of: GraphEventRecordNodeGetEvent
static int	ncuGraphEventWaitNodeGetEvent(long hNode, long event_out)	Unsafe version of: GraphEventWaitNodeGetEvent
static int	ncuGraphExecExternalSemaphoresSignalNodeSetParams(long hGraphExec, long hNode, long nodeParams)	Unsafe version of: GraphExecExternalSemaphoresSignalNodeSetParams
static int	ncuGraphExecExternalSemaphoresWaitNodeSetParams(long hGraphExec, long hNode, long nodeParams)	Unsafe version of: GraphExecExternalSemaphoresWaitNodeSetParams
static int	ncuGraphExecHostNodeSetParams(long hGraphExec, long hNode, long nodeParams)	Unsafe version of: GraphExecHostNodeSetParams
static int	ncuGraphExecKernelNodeSetParams(long hGraphExec, long hNode, long nodeParams)	Unsafe version of: GraphExecKernelNodeSetParams
static int	ncuGraphExecMemcpyNodeSetParams(long hGraphExec, long hNode, long copyParams, long ctx)	Unsafe version of: GraphExecMemcpyNodeSetParams
static int	ncuGraphExecMemsetNodeSetParams(long hGraphExec, long hNode, long memsetParams, long ctx)	Unsafe version of: GraphExecMemsetNodeSetParams
static int	ncuGraphExecUpdate(long hGraphExec, long hGraph, long hErrorNode_out, long updateResult_out)	Unsafe version of: GraphExecUpdate
static int	ncuGraphExternalSemaphoresSignalNodeGetParams(long hNode, long params_out)	Unsafe version of: GraphExternalSemaphoresSignalNodeGetParams
static int	ncuGraphExternalSemaphoresSignalNodeSetParams(long hNode, long nodeParams)	Unsafe version of: GraphExternalSemaphoresSignalNodeSetParams
static int	ncuGraphExternalSemaphoresWaitNodeGetParams(long hNode, long params_out)	Unsafe version of: GraphExternalSemaphoresWaitNodeGetParams
static int	ncuGraphExternalSemaphoresWaitNodeSetParams(long hNode, long nodeParams)	Unsafe version of: GraphExternalSemaphoresWaitNodeSetParams
static int	ncuGraphGetEdges(long hGraph, long from, long to, long numEdges)	Unsafe version of: GraphGetEdges
static int	ncuGraphGetNodes(long hGraph, long nodes, long numNodes)	Unsafe version of: GraphGetNodes
static int	ncuGraphGetRootNodes(long hGraph, long rootNodes, long numRootNodes)	Unsafe version of: GraphGetRootNodes
static int	ncuGraphHostNodeGetParams(long hNode, long nodeParams)	Unsafe version of: GraphHostNodeGetParams
static int	ncuGraphHostNodeSetParams(long hNode, long nodeParams)	Unsafe version of: GraphHostNodeSetParams
static int	ncuGraphicsMapResources(int count, long resources, long hStream)	Unsafe version of: GraphicsMapResources
static int	ncuGraphicsResourceGetMappedMipmappedArray(long pMipmappedArray, long resource)	Unsafe version of: GraphicsResourceGetMappedMipmappedArray
static int	ncuGraphicsResourceGetMappedPointer(long pDevPtr, long pSize, long resource)	Unsafe version of: GraphicsResourceGetMappedPointer
static int	ncuGraphicsSubResourceGetMappedArray(long pArray, long resource, int arrayIndex, int mipLevel)	Unsafe version of: GraphicsSubResourceGetMappedArray
static int	ncuGraphicsUnmapResources(int count, long resources, long hStream)	Unsafe version of: GraphicsUnmapResources
static int	ncuGraphInstantiate(long phGraphExec, long hGraph, long phErrorNode, long logBuffer, long bufferSize)	Unsafe version of: GraphInstantiate
static int	ncuGraphInstantiateWithFlags(long phGraphExec, long hGraph, long flags)	Unsafe version of: GraphInstantiateWithFlags
static int	ncuGraphKernelNodeGetAttribute(long hNode, int attr, long value_out)	Unsafe version of: GraphKernelNodeGetAttribute
static int	ncuGraphKernelNodeGetParams(long hNode, long nodeParams)	Unsafe version of: GraphKernelNodeGetParams
static int	ncuGraphKernelNodeSetAttribute(long hNode, int attr, long value)	Unsafe version of: GraphKernelNodeSetAttribute
static int	ncuGraphKernelNodeSetParams(long hNode, long nodeParams)	Unsafe version of: GraphKernelNodeSetParams
static int	ncuGraphMemAllocNodeGetParams(long hNode, long params_out)	Unsafe version of: GraphMemAllocNodeGetParams
static int	ncuGraphMemcpyNodeGetParams(long hNode, long nodeParams)	Unsafe version of: GraphMemcpyNodeGetParams
static int	ncuGraphMemcpyNodeSetParams(long hNode, long nodeParams)	Unsafe version of: GraphMemcpyNodeSetParams
static int	ncuGraphMemFreeNodeGetParams(long hNode, long dptr_out)	Unsafe version of: GraphMemFreeNodeGetParams
static int	ncuGraphMemsetNodeGetParams(long hNode, long nodeParams)	Unsafe version of: GraphMemsetNodeGetParams
static int	ncuGraphMemsetNodeSetParams(long hNode, long nodeParams)	Unsafe version of: GraphMemsetNodeSetParams
static int	ncuGraphNodeFindInClone(long phNode, long hOriginalNode, long hClonedGraph)	Unsafe version of: GraphNodeFindInClone
static int	ncuGraphNodeGetDependencies(long hNode, long dependencies, long numDependencies)	Unsafe version of: GraphNodeGetDependencies
static int	ncuGraphNodeGetDependentNodes(long hNode, long dependentNodes, long numDependentNodes)	Unsafe version of: GraphNodeGetDependentNodes
static int	ncuGraphNodeGetType(long hNode, long type)	Unsafe version of: GraphNodeGetType
static int	ncuGraphRemoveDependencies(long hGraph, long from, long to, long numDependencies)	Unsafe version of: GraphRemoveDependencies
static int	ncuImportExternalMemory(long extMem_out, long memHandleDesc)	Unsafe version of: ImportExternalMemory
static int	ncuImportExternalSemaphore(long extSem_out, long semHandleDesc)	Unsafe version of: ImportExternalSemaphore
static int	ncuIpcGetEventHandle(long pHandle, long event)	Unsafe version of: IpcGetEventHandle
static int	ncuIpcGetMemHandle(long pHandle, long dptr)	Unsafe version of: IpcGetMemHandle
static int	ncuIpcOpenEventHandle(long phEvent, long handle)	Unsafe version of: IpcOpenEventHandle
static int	ncuIpcOpenMemHandle(long pdptr, long handle, int Flags)	Unsafe version of: IpcOpenMemHandle
static int	ncuLaunchCooperativeKernel(long f, int gridDimX, int gridDimY, int gridDimZ, int blockDimX, int blockDimY, int blockDimZ, int sharedMemBytes, long hStream, long kernelParams)	Unsafe version of: LaunchCooperativeKernel
static int	ncuLaunchCooperativeKernelMultiDevice(long launchParamsList, int numDevices, int flags)	Unsafe version of: LaunchCooperativeKernelMultiDevice
static int	ncuLaunchHostFunc(long hStream, long fn, long userData)	Unsafe version of: LaunchHostFunc
static int	ncuLaunchKernel(long f, int gridDimX, int gridDimY, int gridDimZ, int blockDimX, int blockDimY, int blockDimZ, int sharedMemBytes, long hStream, long kernelParams, long extra)	Unsafe version of: LaunchKernel
static int	ncuLinkAddData(long state, int type, long data, long size, long name, int numOptions, long options, long optionValues)	Unsafe version of: LinkAddData
static int	ncuLinkAddFile(long state, int type, long path, int numOptions, long options, long optionValues)	Unsafe version of: LinkAddFile
static int	ncuLinkComplete(long state, long cubinOut, long sizeOut)	Unsafe version of: LinkComplete
static int	ncuLinkCreate(int numOptions, long options, long optionValues, long stateOut)	Unsafe version of: LinkCreate
static int	ncuMemAddressReserve(long ptr, long size, long alignment, long addr, long flags)	Unsafe version of: MemAddressReserve
static int	ncuMemAlloc(long dptr, long bytesize)	Unsafe version of: MemAlloc
static int	ncuMemAllocAsync(long dptr, long bytesize, long hStream)	Unsafe version of: MemAllocAsync
static int	ncuMemAllocFromPoolAsync(long dptr, long bytesize, long pool, long hStream)	Unsafe version of: MemAllocFromPoolAsync
static int	ncuMemAllocHost(long pp, long bytesize)	Unsafe version of: MemAllocHost
static int	ncuMemAllocManaged(long dptr, long bytesize, int flags)	Unsafe version of: MemAllocManaged
static int	ncuMemAllocPitch(long dptr, long pPitch, long WidthInBytes, long Height, int ElementSizeBytes)	Unsafe version of: MemAllocPitch
static int	ncuMemcpy2D(long pCopy)	Unsafe version of: Memcpy2D
static int	ncuMemcpy2DAsync(long pCopy, long hStream)	Unsafe version of: Memcpy2DAsync
static int	ncuMemcpy2DUnaligned(long pCopy)	Unsafe version of: Memcpy2DUnaligned
static int	ncuMemcpy3D(long pCopy)	Unsafe version of: Memcpy3D
static int	ncuMemcpy3DAsync(long pCopy, long hStream)	Unsafe version of: Memcpy3DAsync
static int	ncuMemcpy3DPeer(long pCopy)	Unsafe version of: Memcpy3DPeer
static int	ncuMemcpy3DPeerAsync(long pCopy, long hStream)	Unsafe version of: Memcpy3DPeerAsync
static int	ncuMemcpyAtoH(long dstHost, long srcArray, long srcOffset, long ByteCount)	Unsafe version of: MemcpyAtoH
static int	ncuMemcpyAtoHAsync(long dstHost, long srcArray, long srcOffset, long ByteCount, long hStream)	Unsafe version of: MemcpyAtoHAsync
static int	ncuMemcpyDtoH(long dstHost, long srcDevice, long ByteCount)	Unsafe version of: MemcpyDtoH
static int	ncuMemcpyDtoHAsync(long dstHost, long srcDevice, long ByteCount, long hStream)	Unsafe version of: MemcpyDtoHAsync
static int	ncuMemcpyHtoA(long dstArray, long dstOffset, long srcHost, long ByteCount)	Unsafe version of: MemcpyHtoA
static int	ncuMemcpyHtoAAsync(long dstArray, long dstOffset, long srcHost, long ByteCount, long hStream)	Unsafe version of: MemcpyHtoAAsync
static int	ncuMemcpyHtoD(long dstDevice, long srcHost, long ByteCount)	Unsafe version of: MemcpyHtoD
static int	ncuMemcpyHtoDAsync(long dstDevice, long srcHost, long ByteCount, long hStream)	Unsafe version of: MemcpyHtoDAsync
static int	ncuMemCreate(long handle, long size, long prop, long flags)	Unsafe version of: MemCreate
static int	ncuMemExportToShareableHandle(long shareableHandle, long handle, int handleType, long flags)	Unsafe version of: MemExportToShareableHandle
static int	ncuMemFreeHost(long p)	Unsafe version of: MemFreeHost
static int	ncuMemGetAccess(long flags, long location, long ptr)	Unsafe version of: MemGetAccess
static int	ncuMemGetAddressRange(long pbase, long psize, long dptr)	Unsafe version of: MemGetAddressRange
static int	ncuMemGetAllocationGranularity(long granularity, long prop, int option)	Unsafe version of: MemGetAllocationGranularity
static int	ncuMemGetAllocationPropertiesFromHandle(long prop, long handle)	Unsafe version of: MemGetAllocationPropertiesFromHandle
static int	ncuMemGetInfo(long free, long total)	Unsafe version of: MemGetInfo
static int	ncuMemHostAlloc(long pp, long bytesize, int Flags)	Unsafe version of: MemHostAlloc
static int	ncuMemHostGetDevicePointer(long pdptr, long p, int Flags)	Unsafe version of: MemHostGetDevicePointer
static int	ncuMemHostGetFlags(long pFlags, long p)	Unsafe version of: MemHostGetFlags
static int	ncuMemHostRegister(long p, long bytesize, int Flags)	Unsafe version of: MemHostRegister
static int	ncuMemHostUnregister(long p)	Unsafe version of: MemHostUnregister
static int	ncuMemImportFromShareableHandle(long handle, long osHandle, int shHandleType)	Unsafe version of: MemImportFromShareableHandle
static int	ncuMemMapArrayAsync(long mapInfoList, int count, long hStream)	Unsafe version of: MemMapArrayAsync
static int	ncuMemPoolCreate(long pool, long poolProps)	Unsafe version of: MemPoolCreate
static int	ncuMemPoolExportPointer(long shareData_out, long ptr)	Unsafe version of: MemPoolExportPointer
static int	ncuMemPoolExportToShareableHandle(long handle_out, long pool, int handleType, long flags)	Unsafe version of: MemPoolExportToShareableHandle
static int	ncuMemPoolGetAccess(long flags, long memPool, long location)	Unsafe version of: MemPoolGetAccess
static int	ncuMemPoolGetAttribute(long pool, int attr, long value)	Unsafe version of: MemPoolGetAttribute
static int	ncuMemPoolImportFromShareableHandle(long pool_out, long handle, int handleType, long flags)	Unsafe version of: MemPoolImportFromShareableHandle
static int	ncuMemPoolImportPointer(long ptr_out, long pool, long shareData)	Unsafe version of: MemPoolImportPointer
static int	ncuMemPoolSetAccess(long pool, long map, long count)	Unsafe version of: MemPoolSetAccess
static int	ncuMemPoolSetAttribute(long pool, int attr, long value)	Unsafe version of: MemPoolSetAttribute
static int	ncuMemRangeGetAttribute(long data, long dataSize, int attribute, long devPtr, long count)	Unsafe version of: MemRangeGetAttribute
static int	ncuMemRangeGetAttributes(long data, long dataSizes, long attributes, long numAttributes, long devPtr, long count)	Unsafe version of: MemRangeGetAttributes
static int	ncuMemRetainAllocationHandle(long handle, long addr)	Unsafe version of: MemRetainAllocationHandle
static int	ncuMemSetAccess(long ptr, long size, long desc, long count)	Unsafe version of: MemSetAccess
static int	ncuMipmappedArrayCreate(long pHandle, long pMipmappedArrayDesc, int numMipmapLevels)	Unsafe version of: MipmappedArrayCreate
static int	ncuMipmappedArrayGetLevel(long pLevelArray, long hMipmappedArray, int level)	Unsafe version of: MipmappedArrayGetLevel
static int	ncuMipmappedArrayGetSparseProperties(long sparseProperties, long mipmap)	Unsafe version of: MipmappedArrayGetSparseProperties
static int	ncuModuleGetFunction(long hfunc, long hmod, long name)	Unsafe version of: ModuleGetFunction
static int	ncuModuleGetGlobal(long dptr, long bytes, long hmod, long name)	Unsafe version of: ModuleGetGlobal
static int	ncuModuleGetSurfRef(long pSurfRef, long hmod, long name)	Unsafe version of: ModuleGetSurfRef
static int	ncuModuleGetTexRef(long pTexRef, long hmod, long name)	Unsafe version of: ModuleGetTexRef
static int	ncuModuleLoad(long module, long fname)	Unsafe version of: ModuleLoad
static int	ncuModuleLoadData(long module, long image)	Unsafe version of: ModuleLoadData
static int	ncuModuleLoadDataEx(long module, long image, int numOptions, long options, long optionValues)	Unsafe version of: ModuleLoadDataEx
static int	ncuModuleLoadFatBinary(long module, long fatCubin)	Unsafe version of: ModuleLoadFatBinary
static int	ncuOccupancyAvailableDynamicSMemPerBlock(long dynamicSmemSize, long func, int numBlocks, int blockSize)	Unsafe version of: OccupancyAvailableDynamicSMemPerBlock
static int	ncuOccupancyMaxActiveBlocksPerMultiprocessor(long numBlocks, long func, int blockSize, long dynamicSMemSize)	Unsafe version of: OccupancyMaxActiveBlocksPerMultiprocessor
static int	ncuOccupancyMaxActiveBlocksPerMultiprocessorWithFlags(long numBlocks, long func, int blockSize, long dynamicSMemSize, int flags)	Unsafe version of: OccupancyMaxActiveBlocksPerMultiprocessorWithFlags
static int	ncuOccupancyMaxPotentialBlockSize(long minGridSize, long blockSize, long func, long blockSizeToDynamicSMemSize, long dynamicSMemSize, int blockSizeLimit)	Unsafe version of: OccupancyMaxPotentialBlockSize
static int	ncuOccupancyMaxPotentialBlockSizeWithFlags(long minGridSize, long blockSize, long func, long blockSizeToDynamicSMemSize, long dynamicSMemSize, int blockSizeLimit, int flags)	Unsafe version of: OccupancyMaxPotentialBlockSizeWithFlags
static int	ncuParamSetv(long hfunc, int offset, long ptr, int numbytes)	Unsafe version of: ParamSetv
static int	ncuPointerGetAttribute(long data, int attribute, long ptr)	Unsafe version of: PointerGetAttribute
static int	ncuPointerGetAttributes(int numAttributes, long attributes, long data, long ptr)	Unsafe version of: PointerGetAttributes
static int	ncuPointerSetAttribute(long value, int attribute, long ptr)	Unsafe version of: PointerSetAttribute
static int	ncuSignalExternalSemaphoresAsync(long extSemArray, long paramsArray, int numExtSems, long stream)	Unsafe version of: SignalExternalSemaphoresAsync
static int	ncuStreamAddCallback(long hStream, long callback, long userData, int flags)	Unsafe version of: StreamAddCallback
static int	ncuStreamBatchMemOp(long stream, int count, long paramArray, int flags)	Unsafe version of: StreamBatchMemOp
static int	ncuStreamCreate(long phStream, int Flags)	Unsafe version of: StreamCreate
static int	ncuStreamCreateWithPriority(long phStream, int flags, int priority)	Unsafe version of: StreamCreateWithPriority
static int	ncuStreamEndCapture(long hStream, long phGraph)	Unsafe version of: StreamEndCapture
static int	ncuStreamGetAttribute(long hStream, int attr, long value_out)	Unsafe version of: StreamGetAttribute
static int	ncuStreamGetCaptureInfo(long hStream, long captureStatus, long id)	Unsafe version of: StreamGetCaptureInfo
static int	ncuStreamGetCaptureInfo_v2(long hStream, long captureStatus_out, long id_out, long graph_out, long dependencies_out, long numDependencies_out)	Unsafe version of: StreamGetCaptureInfo_v2
static int	ncuStreamGetCtx(long hStream, long pctx)	Unsafe version of: StreamGetCtx
static int	ncuStreamGetFlags(long hStream, long flags)	Unsafe version of: StreamGetFlags
static int	ncuStreamGetPriority(long hStream, long priority)	Unsafe version of: StreamGetPriority
static int	ncuStreamIsCapturing(long hStream, long captureStatus)	Unsafe version of: StreamIsCapturing
static int	ncuStreamSetAttribute(long hStream, int attr, long value)	Unsafe version of: StreamSetAttribute
static int	ncuStreamUpdateCaptureDependencies(long hStream, long dependencies, long numDependencies, int flags)	Unsafe version of: StreamUpdateCaptureDependencies
static int	ncuSurfObjectCreate(long pSurfObject, long pResDesc)	Unsafe version of: SurfObjectCreate
static int	ncuSurfObjectGetResourceDesc(long pResDesc, long surfObject)	Unsafe version of: SurfObjectGetResourceDesc
static int	ncuSurfRefGetArray(long phArray, long hSurfRef)	Unsafe version of: SurfRefGetArray
static int	ncuTexObjectCreate(long pTexObject, long pResDesc, long pTexDesc, long pResViewDesc)	Unsafe version of: TexObjectCreate
static int	ncuTexObjectGetResourceDesc(long pResDesc, long texObject)	Unsafe version of: TexObjectGetResourceDesc
static int	ncuTexObjectGetResourceViewDesc(long pResViewDesc, long texObject)	Unsafe version of: TexObjectGetResourceViewDesc
static int	ncuTexObjectGetTextureDesc(long pTexDesc, long texObject)	Unsafe version of: TexObjectGetTextureDesc
static int	ncuTexRefCreate(long pTexRef)	Unsafe version of: TexRefCreate
static int	ncuTexRefGetAddress(long pdptr, long hTexRef)	Unsafe version of: TexRefGetAddress
static int	ncuTexRefGetAddressMode(long pam, long hTexRef, int dim)	Unsafe version of: TexRefGetAddressMode
static int	ncuTexRefGetArray(long phArray, long hTexRef)	Unsafe version of: TexRefGetArray
static int	ncuTexRefGetBorderColor(long pBorderColor, long hTexRef)	Unsafe version of: TexRefGetBorderColor
static int	ncuTexRefGetFilterMode(long pfm, long hTexRef)	Unsafe version of: TexRefGetFilterMode
static int	ncuTexRefGetFlags(long pFlags, long hTexRef)	Unsafe version of: TexRefGetFlags
static int	ncuTexRefGetFormat(long pFormat, long pNumChannels, long hTexRef)	Unsafe version of: TexRefGetFormat
static int	ncuTexRefGetMaxAnisotropy(long pmaxAniso, long hTexRef)	Unsafe version of: TexRefGetMaxAnisotropy
static int	ncuTexRefGetMipmapFilterMode(long pfm, long hTexRef)	Unsafe version of: TexRefGetMipmapFilterMode
static int	ncuTexRefGetMipmapLevelBias(long pbias, long hTexRef)	Unsafe version of: TexRefGetMipmapLevelBias
static int	ncuTexRefGetMipmapLevelClamp(long pminMipmapLevelClamp, long pmaxMipmapLevelClamp, long hTexRef)	Unsafe version of: TexRefGetMipmapLevelClamp
static int	ncuTexRefGetMipmappedArray(long phMipmappedArray, long hTexRef)	Unsafe version of: TexRefGetMipmappedArray
static int	ncuTexRefSetAddress(long ByteOffset, long hTexRef, long dptr, long bytes)	Unsafe version of: TexRefSetAddress
static int	ncuTexRefSetAddress2D(long hTexRef, long desc, long dptr, long Pitch)	Unsafe version of: TexRefSetAddress2D
static int	ncuTexRefSetBorderColor(long hTexRef, long pBorderColor)	Unsafe version of: TexRefSetBorderColor
static int	ncuThreadExchangeStreamCaptureMode(long mode)	Unsafe version of: ThreadExchangeStreamCaptureMode
static int	ncuUserObjectCreate(long object_out, long ptr, long destroy, int initialRefcount, int flags)	Unsafe version of: UserObjectCreate
static int	ncuWaitExternalSemaphoresAsync(long extSemArray, long paramsArray, int numExtSems, long stream)	Unsafe version of: WaitExternalSemaphoresAsync

Methods inherited from class java.lang.Object

equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Field Details

CU_IPC_HANDLE_SIZE

public static final int CU_IPC_HANDLE_SIZE

See Also:

• Constant Field Values

CU_IPC_MEM_LAZY_ENABLE_PEER_ACCESS

public static final int CU_IPC_MEM_LAZY_ENABLE_PEER_ACCESS

CUDA Ipc Mem Flags. (CUipcMem_flags)

Enum values:

• IPC_MEM_LAZY_ENABLE_PEER_ACCESS - Automatically enable peer access between remote devices as needed

See Also:

• Constant Field Values

CU_MEM_ATTACH_GLOBAL

public static final int CU_MEM_ATTACH_GLOBAL

CUDA Mem Attach Flags. (CUmemAttach_flags)

Enum values:

• MEM_ATTACH_GLOBAL - Memory can be accessed by any stream on any device
• MEM_ATTACH_HOST - Memory cannot be accessed by any stream on any device
• MEM_ATTACH_SINGLE - Memory can only be accessed by a single stream on the associated device

See Also:

• Constant Field Values

CU_MEM_ATTACH_HOST

public static final int CU_MEM_ATTACH_HOST

CUDA Mem Attach Flags. (CUmemAttach_flags)

Enum values:

• MEM_ATTACH_GLOBAL - Memory can be accessed by any stream on any device
• MEM_ATTACH_HOST - Memory cannot be accessed by any stream on any device
• MEM_ATTACH_SINGLE - Memory can only be accessed by a single stream on the associated device

See Also:

• Constant Field Values

CU_MEM_ATTACH_SINGLE

public static final int CU_MEM_ATTACH_SINGLE

CUDA Mem Attach Flags. (CUmemAttach_flags)

Enum values:

• MEM_ATTACH_GLOBAL - Memory can be accessed by any stream on any device
• MEM_ATTACH_HOST - Memory cannot be accessed by any stream on any device
• MEM_ATTACH_SINGLE - Memory can only be accessed by a single stream on the associated device

See Also:

• Constant Field Values

CU_CTX_SCHED_AUTO

public static final int CU_CTX_SCHED_AUTO

Context creation flags. (CUctx_flags)

Enum values:

• CTX_SCHED_AUTO - Automatic scheduling
• CTX_SCHED_SPIN - Set spin as default scheduling
• CTX_SCHED_YIELD - Set yield as default scheduling
• CTX_SCHED_BLOCKING_SYNC - Set blocking synchronization as default scheduling
• CTX_BLOCKING_SYNC - Set blocking synchronization as default scheduling. This flag was deprecated as of CUDA 4.0 and was replaced with CTX_SCHED_BLOCKING_SYNC.
• CTX_SCHED_MASK
• CTX_MAP_HOST - This flag was deprecated as of CUDA 11.0 and it no longer has any effect.

  All contexts as of CUDA 3.2 behave as though the flag is enabled.

• CTX_LMEM_RESIZE_TO_MAX - Keep local memory allocation after launch
• CTX_FLAGS_MASK

See Also:

• Constant Field Values

CU_CTX_SCHED_SPIN

public static final int CU_CTX_SCHED_SPIN

Context creation flags. (CUctx_flags)

Enum values:

• CTX_SCHED_AUTO - Automatic scheduling
• CTX_SCHED_SPIN - Set spin as default scheduling
• CTX_SCHED_YIELD - Set yield as default scheduling
• CTX_SCHED_BLOCKING_SYNC - Set blocking synchronization as default scheduling
• CTX_BLOCKING_SYNC - Set blocking synchronization as default scheduling. This flag was deprecated as of CUDA 4.0 and was replaced with CTX_SCHED_BLOCKING_SYNC.
• CTX_SCHED_MASK
• CTX_MAP_HOST - This flag was deprecated as of CUDA 11.0 and it no longer has any effect.

  All contexts as of CUDA 3.2 behave as though the flag is enabled.

• CTX_LMEM_RESIZE_TO_MAX - Keep local memory allocation after launch
• CTX_FLAGS_MASK

See Also:

• Constant Field Values

CU_CTX_SCHED_YIELD

public static final int CU_CTX_SCHED_YIELD

Context creation flags. (CUctx_flags)

Enum values:

• CTX_SCHED_AUTO - Automatic scheduling
• CTX_SCHED_SPIN - Set spin as default scheduling
• CTX_SCHED_YIELD - Set yield as default scheduling
• CTX_SCHED_BLOCKING_SYNC - Set blocking synchronization as default scheduling
• CTX_BLOCKING_SYNC - Set blocking synchronization as default scheduling. This flag was deprecated as of CUDA 4.0 and was replaced with CTX_SCHED_BLOCKING_SYNC.
• CTX_SCHED_MASK
• CTX_MAP_HOST - This flag was deprecated as of CUDA 11.0 and it no longer has any effect.

  All contexts as of CUDA 3.2 behave as though the flag is enabled.

• CTX_LMEM_RESIZE_TO_MAX - Keep local memory allocation after launch
• CTX_FLAGS_MASK

See Also:

• Constant Field Values

CU_CTX_SCHED_BLOCKING_SYNC

public static final int CU_CTX_SCHED_BLOCKING_SYNC

Context creation flags. (CUctx_flags)

Enum values:

• CTX_SCHED_AUTO - Automatic scheduling
• CTX_SCHED_SPIN - Set spin as default scheduling
• CTX_SCHED_YIELD - Set yield as default scheduling
• CTX_SCHED_BLOCKING_SYNC - Set blocking synchronization as default scheduling
• CTX_BLOCKING_SYNC - Set blocking synchronization as default scheduling. This flag was deprecated as of CUDA 4.0 and was replaced with CTX_SCHED_BLOCKING_SYNC.
• CTX_SCHED_MASK
• CTX_MAP_HOST - This flag was deprecated as of CUDA 11.0 and it no longer has any effect.

  All contexts as of CUDA 3.2 behave as though the flag is enabled.

• CTX_LMEM_RESIZE_TO_MAX - Keep local memory allocation after launch
• CTX_FLAGS_MASK

See Also:

• Constant Field Values

CU_CTX_BLOCKING_SYNC

public static final int CU_CTX_BLOCKING_SYNC

Context creation flags. (CUctx_flags)

Enum values:

• CTX_SCHED_AUTO - Automatic scheduling
• CTX_SCHED_SPIN - Set spin as default scheduling
• CTX_SCHED_YIELD - Set yield as default scheduling
• CTX_SCHED_BLOCKING_SYNC - Set blocking synchronization as default scheduling
• CTX_BLOCKING_SYNC - Set blocking synchronization as default scheduling. This flag was deprecated as of CUDA 4.0 and was replaced with CTX_SCHED_BLOCKING_SYNC.
• CTX_SCHED_MASK
• CTX_MAP_HOST - This flag was deprecated as of CUDA 11.0 and it no longer has any effect.

  All contexts as of CUDA 3.2 behave as though the flag is enabled.

• CTX_LMEM_RESIZE_TO_MAX - Keep local memory allocation after launch
• CTX_FLAGS_MASK

See Also:

• Constant Field Values

CU_CTX_SCHED_MASK

public static final int CU_CTX_SCHED_MASK

Context creation flags. (CUctx_flags)

Enum values:

• CTX_SCHED_AUTO - Automatic scheduling
• CTX_SCHED_SPIN - Set spin as default scheduling
• CTX_SCHED_YIELD - Set yield as default scheduling
• CTX_SCHED_BLOCKING_SYNC - Set blocking synchronization as default scheduling
• CTX_BLOCKING_SYNC - Set blocking synchronization as default scheduling. This flag was deprecated as of CUDA 4.0 and was replaced with CTX_SCHED_BLOCKING_SYNC.
• CTX_SCHED_MASK
• CTX_MAP_HOST - This flag was deprecated as of CUDA 11.0 and it no longer has any effect.

  All contexts as of CUDA 3.2 behave as though the flag is enabled.

• CTX_LMEM_RESIZE_TO_MAX - Keep local memory allocation after launch
• CTX_FLAGS_MASK

See Also:

• Constant Field Values

CU_CTX_MAP_HOST

public static final int CU_CTX_MAP_HOST

Context creation flags. (CUctx_flags)

Enum values:

• CTX_SCHED_AUTO - Automatic scheduling
• CTX_SCHED_SPIN - Set spin as default scheduling
• CTX_SCHED_YIELD - Set yield as default scheduling
• CTX_SCHED_BLOCKING_SYNC - Set blocking synchronization as default scheduling
• CTX_BLOCKING_SYNC - Set blocking synchronization as default scheduling. This flag was deprecated as of CUDA 4.0 and was replaced with CTX_SCHED_BLOCKING_SYNC.
• CTX_SCHED_MASK
• CTX_MAP_HOST - This flag was deprecated as of CUDA 11.0 and it no longer has any effect.

  All contexts as of CUDA 3.2 behave as though the flag is enabled.

• CTX_LMEM_RESIZE_TO_MAX - Keep local memory allocation after launch
• CTX_FLAGS_MASK

See Also:

• Constant Field Values

CU_CTX_LMEM_RESIZE_TO_MAX

public static final int CU_CTX_LMEM_RESIZE_TO_MAX

Context creation flags. (CUctx_flags)

Enum values:

• CTX_SCHED_AUTO - Automatic scheduling
• CTX_SCHED_SPIN - Set spin as default scheduling
• CTX_SCHED_YIELD - Set yield as default scheduling
• CTX_SCHED_BLOCKING_SYNC - Set blocking synchronization as default scheduling
• CTX_BLOCKING_SYNC - Set blocking synchronization as default scheduling. This flag was deprecated as of CUDA 4.0 and was replaced with CTX_SCHED_BLOCKING_SYNC.
• CTX_SCHED_MASK
• CTX_MAP_HOST - This flag was deprecated as of CUDA 11.0 and it no longer has any effect.

  All contexts as of CUDA 3.2 behave as though the flag is enabled.

• CTX_LMEM_RESIZE_TO_MAX - Keep local memory allocation after launch
• CTX_FLAGS_MASK

See Also:

• Constant Field Values

CU_CTX_FLAGS_MASK

public static final int CU_CTX_FLAGS_MASK

Context creation flags. (CUctx_flags)

Enum values:

• CTX_SCHED_AUTO - Automatic scheduling
• CTX_SCHED_SPIN - Set spin as default scheduling
• CTX_SCHED_YIELD - Set yield as default scheduling
• CTX_SCHED_BLOCKING_SYNC - Set blocking synchronization as default scheduling
• CTX_BLOCKING_SYNC - Set blocking synchronization as default scheduling. This flag was deprecated as of CUDA 4.0 and was replaced with CTX_SCHED_BLOCKING_SYNC.
• CTX_SCHED_MASK
• CTX_MAP_HOST - This flag was deprecated as of CUDA 11.0 and it no longer has any effect.

  All contexts as of CUDA 3.2 behave as though the flag is enabled.

• CTX_LMEM_RESIZE_TO_MAX - Keep local memory allocation after launch
• CTX_FLAGS_MASK

See Also:

• Constant Field Values

CU_STREAM_DEFAULT

public static final int CU_STREAM_DEFAULT

Stream creation flags. (CUstream_flags)

Enum values:

• STREAM_DEFAULT - Default stream flag
• STREAM_NON_BLOCKING - Stream does not synchronize with stream 0 (the NULL stream)

See Also:

• Constant Field Values

CU_STREAM_NON_BLOCKING

public static final int CU_STREAM_NON_BLOCKING

Stream creation flags. (CUstream_flags)

Enum values:

• STREAM_DEFAULT - Default stream flag
• STREAM_NON_BLOCKING - Stream does not synchronize with stream 0 (the NULL stream)

See Also:

• Constant Field Values

CU_STREAM_LEGACY

public static final long CU_STREAM_LEGACY

Legacy stream handle.

Stream handle that can be passed as a CUstream to use an implicit stream with legacy synchronization behavior.

See Also:

• Constant Field Values

CU_STREAM_PER_THREAD

public static final long CU_STREAM_PER_THREAD

Per-thread stream handle.

Stream handle that can be passed as a CUstream to use an implicit stream with per-thread synchronization behavior.

See Also:

• Constant Field Values

CU_EVENT_DEFAULT

public static final int CU_EVENT_DEFAULT

Event creation flags. (CUevent_flags)

Enum values:

• EVENT_DEFAULT - Default event flag
• EVENT_BLOCKING_SYNC - Event uses blocking synchronization
• EVENT_DISABLE_TIMING - Event will not record timing data
• EVENT_INTERPROCESS - Event is suitable for interprocess use. EVENT_DISABLE_TIMING must be set

See Also:

• Constant Field Values

CU_EVENT_BLOCKING_SYNC

public static final int CU_EVENT_BLOCKING_SYNC

Event creation flags. (CUevent_flags)

Enum values:

• EVENT_DEFAULT - Default event flag
• EVENT_BLOCKING_SYNC - Event uses blocking synchronization
• EVENT_DISABLE_TIMING - Event will not record timing data
• EVENT_INTERPROCESS - Event is suitable for interprocess use. EVENT_DISABLE_TIMING must be set

See Also:

• Constant Field Values

CU_EVENT_DISABLE_TIMING

public static final int CU_EVENT_DISABLE_TIMING

Event creation flags. (CUevent_flags)

Enum values:

• EVENT_DEFAULT - Default event flag
• EVENT_BLOCKING_SYNC - Event uses blocking synchronization
• EVENT_DISABLE_TIMING - Event will not record timing data
• EVENT_INTERPROCESS - Event is suitable for interprocess use. EVENT_DISABLE_TIMING must be set

See Also:

• Constant Field Values

CU_EVENT_INTERPROCESS

public static final int CU_EVENT_INTERPROCESS

Event creation flags. (CUevent_flags)

Enum values:

• EVENT_DEFAULT - Default event flag
• EVENT_BLOCKING_SYNC - Event uses blocking synchronization
• EVENT_DISABLE_TIMING - Event will not record timing data
• EVENT_INTERPROCESS - Event is suitable for interprocess use. EVENT_DISABLE_TIMING must be set

See Also:

• Constant Field Values

CU_EVENT_RECORD_DEFAULT

public static final int CU_EVENT_RECORD_DEFAULT

Event record flags. (CUevent_record_flags)

Enum values:

• EVENT_RECORD_DEFAULT - Default event record flag
• EVENT_RECORD_EXTERNAL - When using stream capture, create an event record node instead of the default behavior.

  This flag is invalid when used outside of capture.

See Also:

• Constant Field Values

CU_EVENT_RECORD_EXTERNAL

public static final int CU_EVENT_RECORD_EXTERNAL

Event record flags. (CUevent_record_flags)

Enum values:

• EVENT_RECORD_DEFAULT - Default event record flag
• EVENT_RECORD_EXTERNAL - When using stream capture, create an event record node instead of the default behavior.

  This flag is invalid when used outside of capture.

See Also:

• Constant Field Values

CU_EVENT_WAIT_DEFAULT

public static final int CU_EVENT_WAIT_DEFAULT

Event wait flags. (CUevent_wait_flags)

Enum values:

• EVENT_WAIT_DEFAULT - Default event wait flag
• EVENT_WAIT_EXTERNAL - When using stream capture, create an event wait node instead of the default behavior.

  This flag is invalid when used outside of capture.

See Also:

• Constant Field Values

CU_EVENT_WAIT_EXTERNAL

public static final int CU_EVENT_WAIT_EXTERNAL

Event wait flags. (CUevent_wait_flags)

Enum values:

• EVENT_WAIT_DEFAULT - Default event wait flag
• EVENT_WAIT_EXTERNAL - When using stream capture, create an event wait node instead of the default behavior.

  This flag is invalid when used outside of capture.

See Also:

• Constant Field Values

CU_STREAM_WAIT_VALUE_GEQ

public static final int CU_STREAM_WAIT_VALUE_GEQ

Flags for StreamWaitValue32 and StreamWaitValue64. (CUstreamWaitValue_flags)

Enum values:

• STREAM_WAIT_VALUE_GEQ - Wait until (int32_t)(*addr - value) >= 0 (or int64_t for 64 bit values). Note this is a cyclic comparison which ignores wraparound. (Default behavior.)
• STREAM_WAIT_VALUE_EQ - Wait until *addr == value.
• STREAM_WAIT_VALUE_AND - Wait until (*addr & value) != 0.
• STREAM_WAIT_VALUE_NOR - Wait until ~(*addr | value) != 0. Support for this operation can be queried with DeviceGetAttribute and DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR.
• STREAM_WAIT_VALUE_FLUSH - Follow the wait operation with a flush of outstanding remote writes.

  This means that, if a remote write operation is guaranteed to have reached the device before the wait can be satisfied, that write is guaranteed to be visible to downstream device work. The device is permitted to reorder remote writes internally. For example, this flag would be required if two remote writes arrive in a defined order, the wait is satisfied by the second write, and downstream work needs to observe the first write.

  Support for this operation is restricted to selected platforms and can be queried with CU_DEVICE_ATTRIBUTE_CAN_USE_WAIT_VALUE_FLUSH.

See Also:

• Constant Field Values

CU_STREAM_WAIT_VALUE_EQ

public static final int CU_STREAM_WAIT_VALUE_EQ

Flags for StreamWaitValue32 and StreamWaitValue64. (CUstreamWaitValue_flags)

Enum values:

• STREAM_WAIT_VALUE_GEQ - Wait until (int32_t)(*addr - value) >= 0 (or int64_t for 64 bit values). Note this is a cyclic comparison which ignores wraparound. (Default behavior.)
• STREAM_WAIT_VALUE_EQ - Wait until *addr == value.
• STREAM_WAIT_VALUE_AND - Wait until (*addr & value) != 0.
• STREAM_WAIT_VALUE_NOR - Wait until ~(*addr | value) != 0. Support for this operation can be queried with DeviceGetAttribute and DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR.
• STREAM_WAIT_VALUE_FLUSH - Follow the wait operation with a flush of outstanding remote writes.

  This means that, if a remote write operation is guaranteed to have reached the device before the wait can be satisfied, that write is guaranteed to be visible to downstream device work. The device is permitted to reorder remote writes internally. For example, this flag would be required if two remote writes arrive in a defined order, the wait is satisfied by the second write, and downstream work needs to observe the first write.

  Support for this operation is restricted to selected platforms and can be queried with CU_DEVICE_ATTRIBUTE_CAN_USE_WAIT_VALUE_FLUSH.

See Also:

• Constant Field Values

CU_STREAM_WAIT_VALUE_AND

public static final int CU_STREAM_WAIT_VALUE_AND

Flags for StreamWaitValue32 and StreamWaitValue64. (CUstreamWaitValue_flags)

Enum values:

• STREAM_WAIT_VALUE_GEQ - Wait until (int32_t)(*addr - value) >= 0 (or int64_t for 64 bit values). Note this is a cyclic comparison which ignores wraparound. (Default behavior.)
• STREAM_WAIT_VALUE_EQ - Wait until *addr == value.
• STREAM_WAIT_VALUE_AND - Wait until (*addr & value) != 0.
• STREAM_WAIT_VALUE_NOR - Wait until ~(*addr | value) != 0. Support for this operation can be queried with DeviceGetAttribute and DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR.
• STREAM_WAIT_VALUE_FLUSH - Follow the wait operation with a flush of outstanding remote writes.

  This means that, if a remote write operation is guaranteed to have reached the device before the wait can be satisfied, that write is guaranteed to be visible to downstream device work. The device is permitted to reorder remote writes internally. For example, this flag would be required if two remote writes arrive in a defined order, the wait is satisfied by the second write, and downstream work needs to observe the first write.

  Support for this operation is restricted to selected platforms and can be queried with CU_DEVICE_ATTRIBUTE_CAN_USE_WAIT_VALUE_FLUSH.

See Also:

• Constant Field Values

CU_STREAM_WAIT_VALUE_NOR

public static final int CU_STREAM_WAIT_VALUE_NOR

Flags for StreamWaitValue32 and StreamWaitValue64. (CUstreamWaitValue_flags)

Enum values:

• STREAM_WAIT_VALUE_GEQ - Wait until (int32_t)(*addr - value) >= 0 (or int64_t for 64 bit values). Note this is a cyclic comparison which ignores wraparound. (Default behavior.)
• STREAM_WAIT_VALUE_EQ - Wait until *addr == value.
• STREAM_WAIT_VALUE_AND - Wait until (*addr & value) != 0.
• STREAM_WAIT_VALUE_NOR - Wait until ~(*addr | value) != 0. Support for this operation can be queried with DeviceGetAttribute and DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR.
• STREAM_WAIT_VALUE_FLUSH - Follow the wait operation with a flush of outstanding remote writes.

  This means that, if a remote write operation is guaranteed to have reached the device before the wait can be satisfied, that write is guaranteed to be visible to downstream device work. The device is permitted to reorder remote writes internally. For example, this flag would be required if two remote writes arrive in a defined order, the wait is satisfied by the second write, and downstream work needs to observe the first write.

  Support for this operation is restricted to selected platforms and can be queried with CU_DEVICE_ATTRIBUTE_CAN_USE_WAIT_VALUE_FLUSH.

See Also:

• Constant Field Values

CU_STREAM_WAIT_VALUE_FLUSH

public static final int CU_STREAM_WAIT_VALUE_FLUSH

Flags for StreamWaitValue32 and StreamWaitValue64. (CUstreamWaitValue_flags)

Enum values:

• STREAM_WAIT_VALUE_GEQ - Wait until (int32_t)(*addr - value) >= 0 (or int64_t for 64 bit values). Note this is a cyclic comparison which ignores wraparound. (Default behavior.)
• STREAM_WAIT_VALUE_EQ - Wait until *addr == value.
• STREAM_WAIT_VALUE_AND - Wait until (*addr & value) != 0.
• STREAM_WAIT_VALUE_NOR - Wait until ~(*addr | value) != 0. Support for this operation can be queried with DeviceGetAttribute and DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR.
• STREAM_WAIT_VALUE_FLUSH - Follow the wait operation with a flush of outstanding remote writes.

  This means that, if a remote write operation is guaranteed to have reached the device before the wait can be satisfied, that write is guaranteed to be visible to downstream device work. The device is permitted to reorder remote writes internally. For example, this flag would be required if two remote writes arrive in a defined order, the wait is satisfied by the second write, and downstream work needs to observe the first write.

  Support for this operation is restricted to selected platforms and can be queried with CU_DEVICE_ATTRIBUTE_CAN_USE_WAIT_VALUE_FLUSH.

See Also:

• Constant Field Values

CU_STREAM_WRITE_VALUE_DEFAULT

public static final int CU_STREAM_WRITE_VALUE_DEFAULT

Flags for StreamWriteValue32. (CUstreamWriteValue_flags)

Enum values:

• STREAM_WRITE_VALUE_DEFAULT - Default behavior
• STREAM_WRITE_VALUE_NO_MEMORY_BARRIER - Permits the write to be reordered with writes which were issued before it, as a performance optimization.

  Normally, StreamWriteValue32 will provide a memory fence before the write, which has similar semantics to __threadfence_system() but is scoped to the stream rather than a CUDA thread.

See Also:

• Constant Field Values

CU_STREAM_WRITE_VALUE_NO_MEMORY_BARRIER

public static final int CU_STREAM_WRITE_VALUE_NO_MEMORY_BARRIER

Flags for StreamWriteValue32. (CUstreamWriteValue_flags)

Enum values:

• STREAM_WRITE_VALUE_DEFAULT - Default behavior
• STREAM_WRITE_VALUE_NO_MEMORY_BARRIER - Permits the write to be reordered with writes which were issued before it, as a performance optimization.

  Normally, StreamWriteValue32 will provide a memory fence before the write, which has similar semantics to __threadfence_system() but is scoped to the stream rather than a CUDA thread.

See Also:

• Constant Field Values

CU_STREAM_MEM_OP_WAIT_VALUE_32

public static final int CU_STREAM_MEM_OP_WAIT_VALUE_32

Operations for StreamBatchMemOp. (CUstreamBatchMemOpType)

Enum values:

• STREAM_MEM_OP_WAIT_VALUE_32 - Represents a StreamWaitValue32 operation
• STREAM_MEM_OP_WRITE_VALUE_32 - Represents a StreamWriteValue32 operation
• STREAM_MEM_OP_WAIT_VALUE_64 - Represents a StreamWaitValue64 operation
• STREAM_MEM_OP_WRITE_VALUE_64 - Represents a StreamWriteValue64 operation
• STREAM_MEM_OP_FLUSH_REMOTE_WRITES - This has the same effect as STREAM_WAIT_VALUE_FLUSH, but as a standalone operation.

See Also:

• Constant Field Values

CU_STREAM_MEM_OP_WRITE_VALUE_32

public static final int CU_STREAM_MEM_OP_WRITE_VALUE_32

Operations for StreamBatchMemOp. (CUstreamBatchMemOpType)

Enum values:

• STREAM_MEM_OP_WAIT_VALUE_32 - Represents a StreamWaitValue32 operation
• STREAM_MEM_OP_WRITE_VALUE_32 - Represents a StreamWriteValue32 operation
• STREAM_MEM_OP_WAIT_VALUE_64 - Represents a StreamWaitValue64 operation
• STREAM_MEM_OP_WRITE_VALUE_64 - Represents a StreamWriteValue64 operation
• STREAM_MEM_OP_FLUSH_REMOTE_WRITES - This has the same effect as STREAM_WAIT_VALUE_FLUSH, but as a standalone operation.

See Also:

• Constant Field Values

CU_STREAM_MEM_OP_WAIT_VALUE_64

public static final int CU_STREAM_MEM_OP_WAIT_VALUE_64

Operations for StreamBatchMemOp. (CUstreamBatchMemOpType)

Enum values:

• STREAM_MEM_OP_WAIT_VALUE_32 - Represents a StreamWaitValue32 operation
• STREAM_MEM_OP_WRITE_VALUE_32 - Represents a StreamWriteValue32 operation
• STREAM_MEM_OP_WAIT_VALUE_64 - Represents a StreamWaitValue64 operation
• STREAM_MEM_OP_WRITE_VALUE_64 - Represents a StreamWriteValue64 operation
• STREAM_MEM_OP_FLUSH_REMOTE_WRITES - This has the same effect as STREAM_WAIT_VALUE_FLUSH, but as a standalone operation.

See Also:

• Constant Field Values

CU_STREAM_MEM_OP_WRITE_VALUE_64

public static final int CU_STREAM_MEM_OP_WRITE_VALUE_64

Operations for StreamBatchMemOp. (CUstreamBatchMemOpType)

Enum values:

• STREAM_MEM_OP_WAIT_VALUE_32 - Represents a StreamWaitValue32 operation
• STREAM_MEM_OP_WRITE_VALUE_32 - Represents a StreamWriteValue32 operation
• STREAM_MEM_OP_WAIT_VALUE_64 - Represents a StreamWaitValue64 operation
• STREAM_MEM_OP_WRITE_VALUE_64 - Represents a StreamWriteValue64 operation
• STREAM_MEM_OP_FLUSH_REMOTE_WRITES - This has the same effect as STREAM_WAIT_VALUE_FLUSH, but as a standalone operation.

See Also:

• Constant Field Values

CU_STREAM_MEM_OP_FLUSH_REMOTE_WRITES

public static final int CU_STREAM_MEM_OP_FLUSH_REMOTE_WRITES

Operations for StreamBatchMemOp. (CUstreamBatchMemOpType)

Enum values:

• STREAM_MEM_OP_WAIT_VALUE_32 - Represents a StreamWaitValue32 operation
• STREAM_MEM_OP_WRITE_VALUE_32 - Represents a StreamWriteValue32 operation
• STREAM_MEM_OP_WAIT_VALUE_64 - Represents a StreamWaitValue64 operation
• STREAM_MEM_OP_WRITE_VALUE_64 - Represents a StreamWriteValue64 operation
• STREAM_MEM_OP_FLUSH_REMOTE_WRITES - This has the same effect as STREAM_WAIT_VALUE_FLUSH, but as a standalone operation.

See Also:

• Constant Field Values

CU_OCCUPANCY_DEFAULT

public static final int CU_OCCUPANCY_DEFAULT

Occupancy calculator flag. (CUoccupancy_flags)

Enum values:

• OCCUPANCY_DEFAULT - Default behavior
• OCCUPANCY_DISABLE_CACHING_OVERRIDE - Assume global caching is enabled and cannot be automatically turned off

See Also:

• Constant Field Values

CU_OCCUPANCY_DISABLE_CACHING_OVERRIDE

public static final int CU_OCCUPANCY_DISABLE_CACHING_OVERRIDE

Occupancy calculator flag. (CUoccupancy_flags)

Enum values:

• OCCUPANCY_DEFAULT - Default behavior
• OCCUPANCY_DISABLE_CACHING_OVERRIDE - Assume global caching is enabled and cannot be automatically turned off

See Also:

• Constant Field Values

CU_STREAM_ADD_CAPTURE_DEPENDENCIES

public static final int CU_STREAM_ADD_CAPTURE_DEPENDENCIES

Flags for StreamUpdateCaptureDependencies). (CUstreamUpdateCaptureDependencies_flags)

Enum values:

• STREAM_ADD_CAPTURE_DEPENDENCIES - Add new nodes to the dependency set
• STREAM_SET_CAPTURE_DEPENDENCIES - Replace the dependency set with the new nodes

See Also:

• Constant Field Values

CU_STREAM_SET_CAPTURE_DEPENDENCIES

public static final int CU_STREAM_SET_CAPTURE_DEPENDENCIES

Flags for StreamUpdateCaptureDependencies). (CUstreamUpdateCaptureDependencies_flags)

Enum values:

• STREAM_ADD_CAPTURE_DEPENDENCIES - Add new nodes to the dependency set
• STREAM_SET_CAPTURE_DEPENDENCIES - Replace the dependency set with the new nodes

See Also:

• Constant Field Values

CU_AD_FORMAT_UNSIGNED_INT8

public static final int CU_AD_FORMAT_UNSIGNED_INT8

Array formats. (CUarray_format)

Enum values:

• AD_FORMAT_UNSIGNED_INT8 - Unsigned 8-bit integers
• AD_FORMAT_UNSIGNED_INT16 - Unsigned 16-bit integers
• AD_FORMAT_UNSIGNED_INT32 - Unsigned 32-bit integers
• AD_FORMAT_SIGNED_INT8 - Signed 8-bit integers
• AD_FORMAT_SIGNED_INT16 - Signed 16-bit integers
• AD_FORMAT_SIGNED_INT32 - Signed 32-bit integers
• AD_FORMAT_HALF - 16-bit floating point
• AD_FORMAT_FLOAT - 32-bit floating point
• AD_FORMAT_NV12 - 8-bit YUV planar format, with 4:2:0 sampling
• AD_FORMAT_UNORM_INT8X1 - 1 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT8X2 - 2 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT8X4 - 4 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT16X1 - 1 channel unsigned 16-bit normalized integer
• AD_FORMAT_UNORM_INT16X2 - 2 channel unsigned 16-bit normalized integer
• AD_FORMAT_UNORM_INT16X4 - 4 channel unsigned 16-bit normalized integer
• AD_FORMAT_SNORM_INT8X1 - 1 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT8X2 - 2 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT8X4 - 4 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT16X1 - 1 channel signed 16-bit normalized integer
• AD_FORMAT_SNORM_INT16X2 - 2 channel signed 16-bit normalized integer
• AD_FORMAT_SNORM_INT16X4 - 4 channel signed 16-bit normalized integer
• AD_FORMAT_BC1_UNORM - 4 channel unsigned normalized block-compressed (BC1 compression) format
• AD_FORMAT_BC1_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC1 compression) format with sRGB encoding
• AD_FORMAT_BC2_UNORM - 4 channel unsigned normalized block-compressed (BC2 compression) format
• AD_FORMAT_BC2_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC2 compression) format with sRGB encoding
• AD_FORMAT_BC3_UNORM - 4 channel unsigned normalized block-compressed (BC3 compression) format
• AD_FORMAT_BC3_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC3 compression) format with sRGB encoding
• AD_FORMAT_BC4_UNORM - 1 channel unsigned normalized block-compressed (BC4 compression) format
• AD_FORMAT_BC4_SNORM - 1 channel signed normalized block-compressed (BC4 compression) format
• AD_FORMAT_BC5_UNORM - 2 channel unsigned normalized block-compressed (BC5 compression) format
• AD_FORMAT_BC5_SNORM - 2 channel signed normalized block-compressed (BC5 compression) format
• AD_FORMAT_BC6H_UF16 - 3 channel unsigned half-float block-compressed (BC6H compression) format
• AD_FORMAT_BC6H_SF16 - 3 channel signed half-float block-compressed (BC6H compression) format
• AD_FORMAT_BC7_UNORM - 4 channel unsigned normalized block-compressed (BC7 compression) format
• AD_FORMAT_BC7_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC7 compression) format with sRGB encoding

See Also:

• Constant Field Values

CU_AD_FORMAT_UNSIGNED_INT16

public static final int CU_AD_FORMAT_UNSIGNED_INT16

Array formats. (CUarray_format)

Enum values:

• AD_FORMAT_UNSIGNED_INT8 - Unsigned 8-bit integers
• AD_FORMAT_UNSIGNED_INT16 - Unsigned 16-bit integers
• AD_FORMAT_UNSIGNED_INT32 - Unsigned 32-bit integers
• AD_FORMAT_SIGNED_INT8 - Signed 8-bit integers
• AD_FORMAT_SIGNED_INT16 - Signed 16-bit integers
• AD_FORMAT_SIGNED_INT32 - Signed 32-bit integers
• AD_FORMAT_HALF - 16-bit floating point
• AD_FORMAT_FLOAT - 32-bit floating point
• AD_FORMAT_NV12 - 8-bit YUV planar format, with 4:2:0 sampling
• AD_FORMAT_UNORM_INT8X1 - 1 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT8X2 - 2 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT8X4 - 4 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT16X1 - 1 channel unsigned 16-bit normalized integer
• AD_FORMAT_UNORM_INT16X2 - 2 channel unsigned 16-bit normalized integer
• AD_FORMAT_UNORM_INT16X4 - 4 channel unsigned 16-bit normalized integer
• AD_FORMAT_SNORM_INT8X1 - 1 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT8X2 - 2 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT8X4 - 4 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT16X1 - 1 channel signed 16-bit normalized integer
• AD_FORMAT_SNORM_INT16X2 - 2 channel signed 16-bit normalized integer
• AD_FORMAT_SNORM_INT16X4 - 4 channel signed 16-bit normalized integer
• AD_FORMAT_BC1_UNORM - 4 channel unsigned normalized block-compressed (BC1 compression) format
• AD_FORMAT_BC1_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC1 compression) format with sRGB encoding
• AD_FORMAT_BC2_UNORM - 4 channel unsigned normalized block-compressed (BC2 compression) format
• AD_FORMAT_BC2_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC2 compression) format with sRGB encoding
• AD_FORMAT_BC3_UNORM - 4 channel unsigned normalized block-compressed (BC3 compression) format
• AD_FORMAT_BC3_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC3 compression) format with sRGB encoding
• AD_FORMAT_BC4_UNORM - 1 channel unsigned normalized block-compressed (BC4 compression) format
• AD_FORMAT_BC4_SNORM - 1 channel signed normalized block-compressed (BC4 compression) format
• AD_FORMAT_BC5_UNORM - 2 channel unsigned normalized block-compressed (BC5 compression) format
• AD_FORMAT_BC5_SNORM - 2 channel signed normalized block-compressed (BC5 compression) format
• AD_FORMAT_BC6H_UF16 - 3 channel unsigned half-float block-compressed (BC6H compression) format
• AD_FORMAT_BC6H_SF16 - 3 channel signed half-float block-compressed (BC6H compression) format
• AD_FORMAT_BC7_UNORM - 4 channel unsigned normalized block-compressed (BC7 compression) format
• AD_FORMAT_BC7_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC7 compression) format with sRGB encoding

See Also:

• Constant Field Values

CU_AD_FORMAT_UNSIGNED_INT32

public static final int CU_AD_FORMAT_UNSIGNED_INT32

Array formats. (CUarray_format)

Enum values:

• AD_FORMAT_UNSIGNED_INT8 - Unsigned 8-bit integers
• AD_FORMAT_UNSIGNED_INT16 - Unsigned 16-bit integers
• AD_FORMAT_UNSIGNED_INT32 - Unsigned 32-bit integers
• AD_FORMAT_SIGNED_INT8 - Signed 8-bit integers
• AD_FORMAT_SIGNED_INT16 - Signed 16-bit integers
• AD_FORMAT_SIGNED_INT32 - Signed 32-bit integers
• AD_FORMAT_HALF - 16-bit floating point
• AD_FORMAT_FLOAT - 32-bit floating point
• AD_FORMAT_NV12 - 8-bit YUV planar format, with 4:2:0 sampling
• AD_FORMAT_UNORM_INT8X1 - 1 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT8X2 - 2 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT8X4 - 4 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT16X1 - 1 channel unsigned 16-bit normalized integer
• AD_FORMAT_UNORM_INT16X2 - 2 channel unsigned 16-bit normalized integer
• AD_FORMAT_UNORM_INT16X4 - 4 channel unsigned 16-bit normalized integer
• AD_FORMAT_SNORM_INT8X1 - 1 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT8X2 - 2 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT8X4 - 4 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT16X1 - 1 channel signed 16-bit normalized integer
• AD_FORMAT_SNORM_INT16X2 - 2 channel signed 16-bit normalized integer
• AD_FORMAT_SNORM_INT16X4 - 4 channel signed 16-bit normalized integer
• AD_FORMAT_BC1_UNORM - 4 channel unsigned normalized block-compressed (BC1 compression) format
• AD_FORMAT_BC1_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC1 compression) format with sRGB encoding
• AD_FORMAT_BC2_UNORM - 4 channel unsigned normalized block-compressed (BC2 compression) format
• AD_FORMAT_BC2_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC2 compression) format with sRGB encoding
• AD_FORMAT_BC3_UNORM - 4 channel unsigned normalized block-compressed (BC3 compression) format
• AD_FORMAT_BC3_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC3 compression) format with sRGB encoding
• AD_FORMAT_BC4_UNORM - 1 channel unsigned normalized block-compressed (BC4 compression) format
• AD_FORMAT_BC4_SNORM - 1 channel signed normalized block-compressed (BC4 compression) format
• AD_FORMAT_BC5_UNORM - 2 channel unsigned normalized block-compressed (BC5 compression) format
• AD_FORMAT_BC5_SNORM - 2 channel signed normalized block-compressed (BC5 compression) format
• AD_FORMAT_BC6H_UF16 - 3 channel unsigned half-float block-compressed (BC6H compression) format
• AD_FORMAT_BC6H_SF16 - 3 channel signed half-float block-compressed (BC6H compression) format
• AD_FORMAT_BC7_UNORM - 4 channel unsigned normalized block-compressed (BC7 compression) format
• AD_FORMAT_BC7_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC7 compression) format with sRGB encoding

See Also:

• Constant Field Values

CU_AD_FORMAT_SIGNED_INT8

public static final int CU_AD_FORMAT_SIGNED_INT8

Array formats. (CUarray_format)

Enum values:

• AD_FORMAT_UNSIGNED_INT8 - Unsigned 8-bit integers
• AD_FORMAT_UNSIGNED_INT16 - Unsigned 16-bit integers
• AD_FORMAT_UNSIGNED_INT32 - Unsigned 32-bit integers
• AD_FORMAT_SIGNED_INT8 - Signed 8-bit integers
• AD_FORMAT_SIGNED_INT16 - Signed 16-bit integers
• AD_FORMAT_SIGNED_INT32 - Signed 32-bit integers
• AD_FORMAT_HALF - 16-bit floating point
• AD_FORMAT_FLOAT - 32-bit floating point
• AD_FORMAT_NV12 - 8-bit YUV planar format, with 4:2:0 sampling
• AD_FORMAT_UNORM_INT8X1 - 1 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT8X2 - 2 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT8X4 - 4 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT16X1 - 1 channel unsigned 16-bit normalized integer
• AD_FORMAT_UNORM_INT16X2 - 2 channel unsigned 16-bit normalized integer
• AD_FORMAT_UNORM_INT16X4 - 4 channel unsigned 16-bit normalized integer
• AD_FORMAT_SNORM_INT8X1 - 1 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT8X2 - 2 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT8X4 - 4 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT16X1 - 1 channel signed 16-bit normalized integer
• AD_FORMAT_SNORM_INT16X2 - 2 channel signed 16-bit normalized integer
• AD_FORMAT_SNORM_INT16X4 - 4 channel signed 16-bit normalized integer
• AD_FORMAT_BC1_UNORM - 4 channel unsigned normalized block-compressed (BC1 compression) format
• AD_FORMAT_BC1_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC1 compression) format with sRGB encoding
• AD_FORMAT_BC2_UNORM - 4 channel unsigned normalized block-compressed (BC2 compression) format
• AD_FORMAT_BC2_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC2 compression) format with sRGB encoding
• AD_FORMAT_BC3_UNORM - 4 channel unsigned normalized block-compressed (BC3 compression) format
• AD_FORMAT_BC3_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC3 compression) format with sRGB encoding
• AD_FORMAT_BC4_UNORM - 1 channel unsigned normalized block-compressed (BC4 compression) format
• AD_FORMAT_BC4_SNORM - 1 channel signed normalized block-compressed (BC4 compression) format
• AD_FORMAT_BC5_UNORM - 2 channel unsigned normalized block-compressed (BC5 compression) format
• AD_FORMAT_BC5_SNORM - 2 channel signed normalized block-compressed (BC5 compression) format
• AD_FORMAT_BC6H_UF16 - 3 channel unsigned half-float block-compressed (BC6H compression) format
• AD_FORMAT_BC6H_SF16 - 3 channel signed half-float block-compressed (BC6H compression) format
• AD_FORMAT_BC7_UNORM - 4 channel unsigned normalized block-compressed (BC7 compression) format
• AD_FORMAT_BC7_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC7 compression) format with sRGB encoding

See Also:

• Constant Field Values

CU_AD_FORMAT_SIGNED_INT16

public static final int CU_AD_FORMAT_SIGNED_INT16

Array formats. (CUarray_format)

Enum values:

• AD_FORMAT_UNSIGNED_INT8 - Unsigned 8-bit integers
• AD_FORMAT_UNSIGNED_INT16 - Unsigned 16-bit integers
• AD_FORMAT_UNSIGNED_INT32 - Unsigned 32-bit integers
• AD_FORMAT_SIGNED_INT8 - Signed 8-bit integers
• AD_FORMAT_SIGNED_INT16 - Signed 16-bit integers
• AD_FORMAT_SIGNED_INT32 - Signed 32-bit integers
• AD_FORMAT_HALF - 16-bit floating point
• AD_FORMAT_FLOAT - 32-bit floating point
• AD_FORMAT_NV12 - 8-bit YUV planar format, with 4:2:0 sampling
• AD_FORMAT_UNORM_INT8X1 - 1 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT8X2 - 2 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT8X4 - 4 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT16X1 - 1 channel unsigned 16-bit normalized integer
• AD_FORMAT_UNORM_INT16X2 - 2 channel unsigned 16-bit normalized integer
• AD_FORMAT_UNORM_INT16X4 - 4 channel unsigned 16-bit normalized integer
• AD_FORMAT_SNORM_INT8X1 - 1 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT8X2 - 2 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT8X4 - 4 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT16X1 - 1 channel signed 16-bit normalized integer
• AD_FORMAT_SNORM_INT16X2 - 2 channel signed 16-bit normalized integer
• AD_FORMAT_SNORM_INT16X4 - 4 channel signed 16-bit normalized integer
• AD_FORMAT_BC1_UNORM - 4 channel unsigned normalized block-compressed (BC1 compression) format
• AD_FORMAT_BC1_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC1 compression) format with sRGB encoding
• AD_FORMAT_BC2_UNORM - 4 channel unsigned normalized block-compressed (BC2 compression) format
• AD_FORMAT_BC2_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC2 compression) format with sRGB encoding
• AD_FORMAT_BC3_UNORM - 4 channel unsigned normalized block-compressed (BC3 compression) format
• AD_FORMAT_BC3_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC3 compression) format with sRGB encoding
• AD_FORMAT_BC4_UNORM - 1 channel unsigned normalized block-compressed (BC4 compression) format
• AD_FORMAT_BC4_SNORM - 1 channel signed normalized block-compressed (BC4 compression) format
• AD_FORMAT_BC5_UNORM - 2 channel unsigned normalized block-compressed (BC5 compression) format
• AD_FORMAT_BC5_SNORM - 2 channel signed normalized block-compressed (BC5 compression) format
• AD_FORMAT_BC6H_UF16 - 3 channel unsigned half-float block-compressed (BC6H compression) format
• AD_FORMAT_BC6H_SF16 - 3 channel signed half-float block-compressed (BC6H compression) format
• AD_FORMAT_BC7_UNORM - 4 channel unsigned normalized block-compressed (BC7 compression) format
• AD_FORMAT_BC7_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC7 compression) format with sRGB encoding

See Also:

• Constant Field Values

CU_AD_FORMAT_SIGNED_INT32

public static final int CU_AD_FORMAT_SIGNED_INT32

Array formats. (CUarray_format)

Enum values:

• AD_FORMAT_UNSIGNED_INT8 - Unsigned 8-bit integers
• AD_FORMAT_UNSIGNED_INT16 - Unsigned 16-bit integers
• AD_FORMAT_UNSIGNED_INT32 - Unsigned 32-bit integers
• AD_FORMAT_SIGNED_INT8 - Signed 8-bit integers
• AD_FORMAT_SIGNED_INT16 - Signed 16-bit integers
• AD_FORMAT_SIGNED_INT32 - Signed 32-bit integers
• AD_FORMAT_HALF - 16-bit floating point
• AD_FORMAT_FLOAT - 32-bit floating point
• AD_FORMAT_NV12 - 8-bit YUV planar format, with 4:2:0 sampling
• AD_FORMAT_UNORM_INT8X1 - 1 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT8X2 - 2 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT8X4 - 4 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT16X1 - 1 channel unsigned 16-bit normalized integer
• AD_FORMAT_UNORM_INT16X2 - 2 channel unsigned 16-bit normalized integer
• AD_FORMAT_UNORM_INT16X4 - 4 channel unsigned 16-bit normalized integer
• AD_FORMAT_SNORM_INT8X1 - 1 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT8X2 - 2 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT8X4 - 4 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT16X1 - 1 channel signed 16-bit normalized integer
• AD_FORMAT_SNORM_INT16X2 - 2 channel signed 16-bit normalized integer
• AD_FORMAT_SNORM_INT16X4 - 4 channel signed 16-bit normalized integer
• AD_FORMAT_BC1_UNORM - 4 channel unsigned normalized block-compressed (BC1 compression) format
• AD_FORMAT_BC1_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC1 compression) format with sRGB encoding
• AD_FORMAT_BC2_UNORM - 4 channel unsigned normalized block-compressed (BC2 compression) format
• AD_FORMAT_BC2_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC2 compression) format with sRGB encoding
• AD_FORMAT_BC3_UNORM - 4 channel unsigned normalized block-compressed (BC3 compression) format
• AD_FORMAT_BC3_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC3 compression) format with sRGB encoding
• AD_FORMAT_BC4_UNORM - 1 channel unsigned normalized block-compressed (BC4 compression) format
• AD_FORMAT_BC4_SNORM - 1 channel signed normalized block-compressed (BC4 compression) format
• AD_FORMAT_BC5_UNORM - 2 channel unsigned normalized block-compressed (BC5 compression) format
• AD_FORMAT_BC5_SNORM - 2 channel signed normalized block-compressed (BC5 compression) format
• AD_FORMAT_BC6H_UF16 - 3 channel unsigned half-float block-compressed (BC6H compression) format
• AD_FORMAT_BC6H_SF16 - 3 channel signed half-float block-compressed (BC6H compression) format
• AD_FORMAT_BC7_UNORM - 4 channel unsigned normalized block-compressed (BC7 compression) format
• AD_FORMAT_BC7_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC7 compression) format with sRGB encoding

See Also:

• Constant Field Values

CU_AD_FORMAT_HALF

public static final int CU_AD_FORMAT_HALF

Array formats. (CUarray_format)

Enum values:

• AD_FORMAT_UNSIGNED_INT8 - Unsigned 8-bit integers
• AD_FORMAT_UNSIGNED_INT16 - Unsigned 16-bit integers
• AD_FORMAT_UNSIGNED_INT32 - Unsigned 32-bit integers
• AD_FORMAT_SIGNED_INT8 - Signed 8-bit integers
• AD_FORMAT_SIGNED_INT16 - Signed 16-bit integers
• AD_FORMAT_SIGNED_INT32 - Signed 32-bit integers
• AD_FORMAT_HALF - 16-bit floating point
• AD_FORMAT_FLOAT - 32-bit floating point
• AD_FORMAT_NV12 - 8-bit YUV planar format, with 4:2:0 sampling
• AD_FORMAT_UNORM_INT8X1 - 1 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT8X2 - 2 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT8X4 - 4 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT16X1 - 1 channel unsigned 16-bit normalized integer
• AD_FORMAT_UNORM_INT16X2 - 2 channel unsigned 16-bit normalized integer
• AD_FORMAT_UNORM_INT16X4 - 4 channel unsigned 16-bit normalized integer
• AD_FORMAT_SNORM_INT8X1 - 1 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT8X2 - 2 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT8X4 - 4 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT16X1 - 1 channel signed 16-bit normalized integer
• AD_FORMAT_SNORM_INT16X2 - 2 channel signed 16-bit normalized integer
• AD_FORMAT_SNORM_INT16X4 - 4 channel signed 16-bit normalized integer
• AD_FORMAT_BC1_UNORM - 4 channel unsigned normalized block-compressed (BC1 compression) format
• AD_FORMAT_BC1_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC1 compression) format with sRGB encoding
• AD_FORMAT_BC2_UNORM - 4 channel unsigned normalized block-compressed (BC2 compression) format
• AD_FORMAT_BC2_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC2 compression) format with sRGB encoding
• AD_FORMAT_BC3_UNORM - 4 channel unsigned normalized block-compressed (BC3 compression) format
• AD_FORMAT_BC3_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC3 compression) format with sRGB encoding
• AD_FORMAT_BC4_UNORM - 1 channel unsigned normalized block-compressed (BC4 compression) format
• AD_FORMAT_BC4_SNORM - 1 channel signed normalized block-compressed (BC4 compression) format
• AD_FORMAT_BC5_UNORM - 2 channel unsigned normalized block-compressed (BC5 compression) format
• AD_FORMAT_BC5_SNORM - 2 channel signed normalized block-compressed (BC5 compression) format
• AD_FORMAT_BC6H_UF16 - 3 channel unsigned half-float block-compressed (BC6H compression) format
• AD_FORMAT_BC6H_SF16 - 3 channel signed half-float block-compressed (BC6H compression) format
• AD_FORMAT_BC7_UNORM - 4 channel unsigned normalized block-compressed (BC7 compression) format
• AD_FORMAT_BC7_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC7 compression) format with sRGB encoding

See Also:

• Constant Field Values

CU_AD_FORMAT_FLOAT

public static final int CU_AD_FORMAT_FLOAT

Array formats. (CUarray_format)

Enum values:

• AD_FORMAT_UNSIGNED_INT8 - Unsigned 8-bit integers
• AD_FORMAT_UNSIGNED_INT16 - Unsigned 16-bit integers
• AD_FORMAT_UNSIGNED_INT32 - Unsigned 32-bit integers
• AD_FORMAT_SIGNED_INT8 - Signed 8-bit integers
• AD_FORMAT_SIGNED_INT16 - Signed 16-bit integers
• AD_FORMAT_SIGNED_INT32 - Signed 32-bit integers
• AD_FORMAT_HALF - 16-bit floating point
• AD_FORMAT_FLOAT - 32-bit floating point
• AD_FORMAT_NV12 - 8-bit YUV planar format, with 4:2:0 sampling
• AD_FORMAT_UNORM_INT8X1 - 1 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT8X2 - 2 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT8X4 - 4 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT16X1 - 1 channel unsigned 16-bit normalized integer
• AD_FORMAT_UNORM_INT16X2 - 2 channel unsigned 16-bit normalized integer
• AD_FORMAT_UNORM_INT16X4 - 4 channel unsigned 16-bit normalized integer
• AD_FORMAT_SNORM_INT8X1 - 1 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT8X2 - 2 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT8X4 - 4 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT16X1 - 1 channel signed 16-bit normalized integer
• AD_FORMAT_SNORM_INT16X2 - 2 channel signed 16-bit normalized integer
• AD_FORMAT_SNORM_INT16X4 - 4 channel signed 16-bit normalized integer
• AD_FORMAT_BC1_UNORM - 4 channel unsigned normalized block-compressed (BC1 compression) format
• AD_FORMAT_BC1_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC1 compression) format with sRGB encoding
• AD_FORMAT_BC2_UNORM - 4 channel unsigned normalized block-compressed (BC2 compression) format
• AD_FORMAT_BC2_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC2 compression) format with sRGB encoding
• AD_FORMAT_BC3_UNORM - 4 channel unsigned normalized block-compressed (BC3 compression) format
• AD_FORMAT_BC3_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC3 compression) format with sRGB encoding
• AD_FORMAT_BC4_UNORM - 1 channel unsigned normalized block-compressed (BC4 compression) format
• AD_FORMAT_BC4_SNORM - 1 channel signed normalized block-compressed (BC4 compression) format
• AD_FORMAT_BC5_UNORM - 2 channel unsigned normalized block-compressed (BC5 compression) format
• AD_FORMAT_BC5_SNORM - 2 channel signed normalized block-compressed (BC5 compression) format
• AD_FORMAT_BC6H_UF16 - 3 channel unsigned half-float block-compressed (BC6H compression) format
• AD_FORMAT_BC6H_SF16 - 3 channel signed half-float block-compressed (BC6H compression) format
• AD_FORMAT_BC7_UNORM - 4 channel unsigned normalized block-compressed (BC7 compression) format
• AD_FORMAT_BC7_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC7 compression) format with sRGB encoding

See Also:

• Constant Field Values

CU_AD_FORMAT_NV12

public static final int CU_AD_FORMAT_NV12

Array formats. (CUarray_format)

Enum values:

• AD_FORMAT_UNSIGNED_INT8 - Unsigned 8-bit integers
• AD_FORMAT_UNSIGNED_INT16 - Unsigned 16-bit integers
• AD_FORMAT_UNSIGNED_INT32 - Unsigned 32-bit integers
• AD_FORMAT_SIGNED_INT8 - Signed 8-bit integers
• AD_FORMAT_SIGNED_INT16 - Signed 16-bit integers
• AD_FORMAT_SIGNED_INT32 - Signed 32-bit integers
• AD_FORMAT_HALF - 16-bit floating point
• AD_FORMAT_FLOAT - 32-bit floating point
• AD_FORMAT_NV12 - 8-bit YUV planar format, with 4:2:0 sampling
• AD_FORMAT_UNORM_INT8X1 - 1 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT8X2 - 2 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT8X4 - 4 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT16X1 - 1 channel unsigned 16-bit normalized integer
• AD_FORMAT_UNORM_INT16X2 - 2 channel unsigned 16-bit normalized integer
• AD_FORMAT_UNORM_INT16X4 - 4 channel unsigned 16-bit normalized integer
• AD_FORMAT_SNORM_INT8X1 - 1 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT8X2 - 2 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT8X4 - 4 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT16X1 - 1 channel signed 16-bit normalized integer
• AD_FORMAT_SNORM_INT16X2 - 2 channel signed 16-bit normalized integer
• AD_FORMAT_SNORM_INT16X4 - 4 channel signed 16-bit normalized integer
• AD_FORMAT_BC1_UNORM - 4 channel unsigned normalized block-compressed (BC1 compression) format
• AD_FORMAT_BC1_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC1 compression) format with sRGB encoding
• AD_FORMAT_BC2_UNORM - 4 channel unsigned normalized block-compressed (BC2 compression) format
• AD_FORMAT_BC2_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC2 compression) format with sRGB encoding
• AD_FORMAT_BC3_UNORM - 4 channel unsigned normalized block-compressed (BC3 compression) format
• AD_FORMAT_BC3_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC3 compression) format with sRGB encoding
• AD_FORMAT_BC4_UNORM - 1 channel unsigned normalized block-compressed (BC4 compression) format
• AD_FORMAT_BC4_SNORM - 1 channel signed normalized block-compressed (BC4 compression) format
• AD_FORMAT_BC5_UNORM - 2 channel unsigned normalized block-compressed (BC5 compression) format
• AD_FORMAT_BC5_SNORM - 2 channel signed normalized block-compressed (BC5 compression) format
• AD_FORMAT_BC6H_UF16 - 3 channel unsigned half-float block-compressed (BC6H compression) format
• AD_FORMAT_BC6H_SF16 - 3 channel signed half-float block-compressed (BC6H compression) format
• AD_FORMAT_BC7_UNORM - 4 channel unsigned normalized block-compressed (BC7 compression) format
• AD_FORMAT_BC7_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC7 compression) format with sRGB encoding

See Also:

• Constant Field Values

CU_AD_FORMAT_UNORM_INT8X1

public static final int CU_AD_FORMAT_UNORM_INT8X1

Array formats. (CUarray_format)

Enum values:

• AD_FORMAT_UNSIGNED_INT8 - Unsigned 8-bit integers
• AD_FORMAT_UNSIGNED_INT16 - Unsigned 16-bit integers
• AD_FORMAT_UNSIGNED_INT32 - Unsigned 32-bit integers
• AD_FORMAT_SIGNED_INT8 - Signed 8-bit integers
• AD_FORMAT_SIGNED_INT16 - Signed 16-bit integers
• AD_FORMAT_SIGNED_INT32 - Signed 32-bit integers
• AD_FORMAT_HALF - 16-bit floating point
• AD_FORMAT_FLOAT - 32-bit floating point
• AD_FORMAT_NV12 - 8-bit YUV planar format, with 4:2:0 sampling
• AD_FORMAT_UNORM_INT8X1 - 1 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT8X2 - 2 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT8X4 - 4 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT16X1 - 1 channel unsigned 16-bit normalized integer
• AD_FORMAT_UNORM_INT16X2 - 2 channel unsigned 16-bit normalized integer
• AD_FORMAT_UNORM_INT16X4 - 4 channel unsigned 16-bit normalized integer
• AD_FORMAT_SNORM_INT8X1 - 1 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT8X2 - 2 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT8X4 - 4 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT16X1 - 1 channel signed 16-bit normalized integer
• AD_FORMAT_SNORM_INT16X2 - 2 channel signed 16-bit normalized integer
• AD_FORMAT_SNORM_INT16X4 - 4 channel signed 16-bit normalized integer
• AD_FORMAT_BC1_UNORM - 4 channel unsigned normalized block-compressed (BC1 compression) format
• AD_FORMAT_BC1_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC1 compression) format with sRGB encoding
• AD_FORMAT_BC2_UNORM - 4 channel unsigned normalized block-compressed (BC2 compression) format
• AD_FORMAT_BC2_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC2 compression) format with sRGB encoding
• AD_FORMAT_BC3_UNORM - 4 channel unsigned normalized block-compressed (BC3 compression) format
• AD_FORMAT_BC3_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC3 compression) format with sRGB encoding
• AD_FORMAT_BC4_UNORM - 1 channel unsigned normalized block-compressed (BC4 compression) format
• AD_FORMAT_BC4_SNORM - 1 channel signed normalized block-compressed (BC4 compression) format
• AD_FORMAT_BC5_UNORM - 2 channel unsigned normalized block-compressed (BC5 compression) format
• AD_FORMAT_BC5_SNORM - 2 channel signed normalized block-compressed (BC5 compression) format
• AD_FORMAT_BC6H_UF16 - 3 channel unsigned half-float block-compressed (BC6H compression) format
• AD_FORMAT_BC6H_SF16 - 3 channel signed half-float block-compressed (BC6H compression) format
• AD_FORMAT_BC7_UNORM - 4 channel unsigned normalized block-compressed (BC7 compression) format
• AD_FORMAT_BC7_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC7 compression) format with sRGB encoding

See Also:

• Constant Field Values

CU_AD_FORMAT_UNORM_INT8X2

public static final int CU_AD_FORMAT_UNORM_INT8X2

Array formats. (CUarray_format)

Enum values:

• AD_FORMAT_UNSIGNED_INT8 - Unsigned 8-bit integers
• AD_FORMAT_UNSIGNED_INT16 - Unsigned 16-bit integers
• AD_FORMAT_UNSIGNED_INT32 - Unsigned 32-bit integers
• AD_FORMAT_SIGNED_INT8 - Signed 8-bit integers
• AD_FORMAT_SIGNED_INT16 - Signed 16-bit integers
• AD_FORMAT_SIGNED_INT32 - Signed 32-bit integers
• AD_FORMAT_HALF - 16-bit floating point
• AD_FORMAT_FLOAT - 32-bit floating point
• AD_FORMAT_NV12 - 8-bit YUV planar format, with 4:2:0 sampling
• AD_FORMAT_UNORM_INT8X1 - 1 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT8X2 - 2 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT8X4 - 4 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT16X1 - 1 channel unsigned 16-bit normalized integer
• AD_FORMAT_UNORM_INT16X2 - 2 channel unsigned 16-bit normalized integer
• AD_FORMAT_UNORM_INT16X4 - 4 channel unsigned 16-bit normalized integer
• AD_FORMAT_SNORM_INT8X1 - 1 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT8X2 - 2 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT8X4 - 4 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT16X1 - 1 channel signed 16-bit normalized integer
• AD_FORMAT_SNORM_INT16X2 - 2 channel signed 16-bit normalized integer
• AD_FORMAT_SNORM_INT16X4 - 4 channel signed 16-bit normalized integer
• AD_FORMAT_BC1_UNORM - 4 channel unsigned normalized block-compressed (BC1 compression) format
• AD_FORMAT_BC1_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC1 compression) format with sRGB encoding
• AD_FORMAT_BC2_UNORM - 4 channel unsigned normalized block-compressed (BC2 compression) format
• AD_FORMAT_BC2_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC2 compression) format with sRGB encoding
• AD_FORMAT_BC3_UNORM - 4 channel unsigned normalized block-compressed (BC3 compression) format
• AD_FORMAT_BC3_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC3 compression) format with sRGB encoding
• AD_FORMAT_BC4_UNORM - 1 channel unsigned normalized block-compressed (BC4 compression) format
• AD_FORMAT_BC4_SNORM - 1 channel signed normalized block-compressed (BC4 compression) format
• AD_FORMAT_BC5_UNORM - 2 channel unsigned normalized block-compressed (BC5 compression) format
• AD_FORMAT_BC5_SNORM - 2 channel signed normalized block-compressed (BC5 compression) format
• AD_FORMAT_BC6H_UF16 - 3 channel unsigned half-float block-compressed (BC6H compression) format
• AD_FORMAT_BC6H_SF16 - 3 channel signed half-float block-compressed (BC6H compression) format
• AD_FORMAT_BC7_UNORM - 4 channel unsigned normalized block-compressed (BC7 compression) format
• AD_FORMAT_BC7_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC7 compression) format with sRGB encoding

See Also:

• Constant Field Values

CU_AD_FORMAT_UNORM_INT8X4

public static final int CU_AD_FORMAT_UNORM_INT8X4

Array formats. (CUarray_format)

Enum values:

• AD_FORMAT_UNSIGNED_INT8 - Unsigned 8-bit integers
• AD_FORMAT_UNSIGNED_INT16 - Unsigned 16-bit integers
• AD_FORMAT_UNSIGNED_INT32 - Unsigned 32-bit integers
• AD_FORMAT_SIGNED_INT8 - Signed 8-bit integers
• AD_FORMAT_SIGNED_INT16 - Signed 16-bit integers
• AD_FORMAT_SIGNED_INT32 - Signed 32-bit integers
• AD_FORMAT_HALF - 16-bit floating point
• AD_FORMAT_FLOAT - 32-bit floating point
• AD_FORMAT_NV12 - 8-bit YUV planar format, with 4:2:0 sampling
• AD_FORMAT_UNORM_INT8X1 - 1 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT8X2 - 2 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT8X4 - 4 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT16X1 - 1 channel unsigned 16-bit normalized integer
• AD_FORMAT_UNORM_INT16X2 - 2 channel unsigned 16-bit normalized integer
• AD_FORMAT_UNORM_INT16X4 - 4 channel unsigned 16-bit normalized integer
• AD_FORMAT_SNORM_INT8X1 - 1 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT8X2 - 2 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT8X4 - 4 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT16X1 - 1 channel signed 16-bit normalized integer
• AD_FORMAT_SNORM_INT16X2 - 2 channel signed 16-bit normalized integer
• AD_FORMAT_SNORM_INT16X4 - 4 channel signed 16-bit normalized integer
• AD_FORMAT_BC1_UNORM - 4 channel unsigned normalized block-compressed (BC1 compression) format
• AD_FORMAT_BC1_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC1 compression) format with sRGB encoding
• AD_FORMAT_BC2_UNORM - 4 channel unsigned normalized block-compressed (BC2 compression) format
• AD_FORMAT_BC2_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC2 compression) format with sRGB encoding
• AD_FORMAT_BC3_UNORM - 4 channel unsigned normalized block-compressed (BC3 compression) format
• AD_FORMAT_BC3_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC3 compression) format with sRGB encoding
• AD_FORMAT_BC4_UNORM - 1 channel unsigned normalized block-compressed (BC4 compression) format
• AD_FORMAT_BC4_SNORM - 1 channel signed normalized block-compressed (BC4 compression) format
• AD_FORMAT_BC5_UNORM - 2 channel unsigned normalized block-compressed (BC5 compression) format
• AD_FORMAT_BC5_SNORM - 2 channel signed normalized block-compressed (BC5 compression) format
• AD_FORMAT_BC6H_UF16 - 3 channel unsigned half-float block-compressed (BC6H compression) format
• AD_FORMAT_BC6H_SF16 - 3 channel signed half-float block-compressed (BC6H compression) format
• AD_FORMAT_BC7_UNORM - 4 channel unsigned normalized block-compressed (BC7 compression) format
• AD_FORMAT_BC7_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC7 compression) format with sRGB encoding

See Also:

• Constant Field Values

CU_AD_FORMAT_UNORM_INT16X1

public static final int CU_AD_FORMAT_UNORM_INT16X1

Array formats. (CUarray_format)

Enum values:

• AD_FORMAT_UNSIGNED_INT8 - Unsigned 8-bit integers
• AD_FORMAT_UNSIGNED_INT16 - Unsigned 16-bit integers
• AD_FORMAT_UNSIGNED_INT32 - Unsigned 32-bit integers
• AD_FORMAT_SIGNED_INT8 - Signed 8-bit integers
• AD_FORMAT_SIGNED_INT16 - Signed 16-bit integers
• AD_FORMAT_SIGNED_INT32 - Signed 32-bit integers
• AD_FORMAT_HALF - 16-bit floating point
• AD_FORMAT_FLOAT - 32-bit floating point
• AD_FORMAT_NV12 - 8-bit YUV planar format, with 4:2:0 sampling
• AD_FORMAT_UNORM_INT8X1 - 1 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT8X2 - 2 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT8X4 - 4 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT16X1 - 1 channel unsigned 16-bit normalized integer
• AD_FORMAT_UNORM_INT16X2 - 2 channel unsigned 16-bit normalized integer
• AD_FORMAT_UNORM_INT16X4 - 4 channel unsigned 16-bit normalized integer
• AD_FORMAT_SNORM_INT8X1 - 1 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT8X2 - 2 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT8X4 - 4 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT16X1 - 1 channel signed 16-bit normalized integer
• AD_FORMAT_SNORM_INT16X2 - 2 channel signed 16-bit normalized integer
• AD_FORMAT_SNORM_INT16X4 - 4 channel signed 16-bit normalized integer
• AD_FORMAT_BC1_UNORM - 4 channel unsigned normalized block-compressed (BC1 compression) format
• AD_FORMAT_BC1_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC1 compression) format with sRGB encoding
• AD_FORMAT_BC2_UNORM - 4 channel unsigned normalized block-compressed (BC2 compression) format
• AD_FORMAT_BC2_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC2 compression) format with sRGB encoding
• AD_FORMAT_BC3_UNORM - 4 channel unsigned normalized block-compressed (BC3 compression) format
• AD_FORMAT_BC3_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC3 compression) format with sRGB encoding
• AD_FORMAT_BC4_UNORM - 1 channel unsigned normalized block-compressed (BC4 compression) format
• AD_FORMAT_BC4_SNORM - 1 channel signed normalized block-compressed (BC4 compression) format
• AD_FORMAT_BC5_UNORM - 2 channel unsigned normalized block-compressed (BC5 compression) format
• AD_FORMAT_BC5_SNORM - 2 channel signed normalized block-compressed (BC5 compression) format
• AD_FORMAT_BC6H_UF16 - 3 channel unsigned half-float block-compressed (BC6H compression) format
• AD_FORMAT_BC6H_SF16 - 3 channel signed half-float block-compressed (BC6H compression) format
• AD_FORMAT_BC7_UNORM - 4 channel unsigned normalized block-compressed (BC7 compression) format
• AD_FORMAT_BC7_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC7 compression) format with sRGB encoding

See Also:

• Constant Field Values

CU_AD_FORMAT_UNORM_INT16X2

public static final int CU_AD_FORMAT_UNORM_INT16X2

Array formats. (CUarray_format)

Enum values:

• AD_FORMAT_UNSIGNED_INT8 - Unsigned 8-bit integers
• AD_FORMAT_UNSIGNED_INT16 - Unsigned 16-bit integers
• AD_FORMAT_UNSIGNED_INT32 - Unsigned 32-bit integers
• AD_FORMAT_SIGNED_INT8 - Signed 8-bit integers
• AD_FORMAT_SIGNED_INT16 - Signed 16-bit integers
• AD_FORMAT_SIGNED_INT32 - Signed 32-bit integers
• AD_FORMAT_HALF - 16-bit floating point
• AD_FORMAT_FLOAT - 32-bit floating point
• AD_FORMAT_NV12 - 8-bit YUV planar format, with 4:2:0 sampling
• AD_FORMAT_UNORM_INT8X1 - 1 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT8X2 - 2 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT8X4 - 4 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT16X1 - 1 channel unsigned 16-bit normalized integer
• AD_FORMAT_UNORM_INT16X2 - 2 channel unsigned 16-bit normalized integer
• AD_FORMAT_UNORM_INT16X4 - 4 channel unsigned 16-bit normalized integer
• AD_FORMAT_SNORM_INT8X1 - 1 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT8X2 - 2 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT8X4 - 4 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT16X1 - 1 channel signed 16-bit normalized integer
• AD_FORMAT_SNORM_INT16X2 - 2 channel signed 16-bit normalized integer
• AD_FORMAT_SNORM_INT16X4 - 4 channel signed 16-bit normalized integer
• AD_FORMAT_BC1_UNORM - 4 channel unsigned normalized block-compressed (BC1 compression) format
• AD_FORMAT_BC1_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC1 compression) format with sRGB encoding
• AD_FORMAT_BC2_UNORM - 4 channel unsigned normalized block-compressed (BC2 compression) format
• AD_FORMAT_BC2_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC2 compression) format with sRGB encoding
• AD_FORMAT_BC3_UNORM - 4 channel unsigned normalized block-compressed (BC3 compression) format
• AD_FORMAT_BC3_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC3 compression) format with sRGB encoding
• AD_FORMAT_BC4_UNORM - 1 channel unsigned normalized block-compressed (BC4 compression) format
• AD_FORMAT_BC4_SNORM - 1 channel signed normalized block-compressed (BC4 compression) format
• AD_FORMAT_BC5_UNORM - 2 channel unsigned normalized block-compressed (BC5 compression) format
• AD_FORMAT_BC5_SNORM - 2 channel signed normalized block-compressed (BC5 compression) format
• AD_FORMAT_BC6H_UF16 - 3 channel unsigned half-float block-compressed (BC6H compression) format
• AD_FORMAT_BC6H_SF16 - 3 channel signed half-float block-compressed (BC6H compression) format
• AD_FORMAT_BC7_UNORM - 4 channel unsigned normalized block-compressed (BC7 compression) format
• AD_FORMAT_BC7_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC7 compression) format with sRGB encoding

See Also:

• Constant Field Values

CU_AD_FORMAT_UNORM_INT16X4

public static final int CU_AD_FORMAT_UNORM_INT16X4

Array formats. (CUarray_format)

Enum values:

• AD_FORMAT_UNSIGNED_INT8 - Unsigned 8-bit integers
• AD_FORMAT_UNSIGNED_INT16 - Unsigned 16-bit integers
• AD_FORMAT_UNSIGNED_INT32 - Unsigned 32-bit integers
• AD_FORMAT_SIGNED_INT8 - Signed 8-bit integers
• AD_FORMAT_SIGNED_INT16 - Signed 16-bit integers
• AD_FORMAT_SIGNED_INT32 - Signed 32-bit integers
• AD_FORMAT_HALF - 16-bit floating point
• AD_FORMAT_FLOAT - 32-bit floating point
• AD_FORMAT_NV12 - 8-bit YUV planar format, with 4:2:0 sampling
• AD_FORMAT_UNORM_INT8X1 - 1 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT8X2 - 2 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT8X4 - 4 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT16X1 - 1 channel unsigned 16-bit normalized integer
• AD_FORMAT_UNORM_INT16X2 - 2 channel unsigned 16-bit normalized integer
• AD_FORMAT_UNORM_INT16X4 - 4 channel unsigned 16-bit normalized integer
• AD_FORMAT_SNORM_INT8X1 - 1 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT8X2 - 2 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT8X4 - 4 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT16X1 - 1 channel signed 16-bit normalized integer
• AD_FORMAT_SNORM_INT16X2 - 2 channel signed 16-bit normalized integer
• AD_FORMAT_SNORM_INT16X4 - 4 channel signed 16-bit normalized integer
• AD_FORMAT_BC1_UNORM - 4 channel unsigned normalized block-compressed (BC1 compression) format
• AD_FORMAT_BC1_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC1 compression) format with sRGB encoding
• AD_FORMAT_BC2_UNORM - 4 channel unsigned normalized block-compressed (BC2 compression) format
• AD_FORMAT_BC2_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC2 compression) format with sRGB encoding
• AD_FORMAT_BC3_UNORM - 4 channel unsigned normalized block-compressed (BC3 compression) format
• AD_FORMAT_BC3_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC3 compression) format with sRGB encoding
• AD_FORMAT_BC4_UNORM - 1 channel unsigned normalized block-compressed (BC4 compression) format
• AD_FORMAT_BC4_SNORM - 1 channel signed normalized block-compressed (BC4 compression) format
• AD_FORMAT_BC5_UNORM - 2 channel unsigned normalized block-compressed (BC5 compression) format
• AD_FORMAT_BC5_SNORM - 2 channel signed normalized block-compressed (BC5 compression) format
• AD_FORMAT_BC6H_UF16 - 3 channel unsigned half-float block-compressed (BC6H compression) format
• AD_FORMAT_BC6H_SF16 - 3 channel signed half-float block-compressed (BC6H compression) format
• AD_FORMAT_BC7_UNORM - 4 channel unsigned normalized block-compressed (BC7 compression) format
• AD_FORMAT_BC7_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC7 compression) format with sRGB encoding

See Also:

• Constant Field Values

CU_AD_FORMAT_SNORM_INT8X1

public static final int CU_AD_FORMAT_SNORM_INT8X1

Array formats. (CUarray_format)

Enum values:

• AD_FORMAT_UNSIGNED_INT8 - Unsigned 8-bit integers
• AD_FORMAT_UNSIGNED_INT16 - Unsigned 16-bit integers
• AD_FORMAT_UNSIGNED_INT32 - Unsigned 32-bit integers
• AD_FORMAT_SIGNED_INT8 - Signed 8-bit integers
• AD_FORMAT_SIGNED_INT16 - Signed 16-bit integers
• AD_FORMAT_SIGNED_INT32 - Signed 32-bit integers
• AD_FORMAT_HALF - 16-bit floating point
• AD_FORMAT_FLOAT - 32-bit floating point
• AD_FORMAT_NV12 - 8-bit YUV planar format, with 4:2:0 sampling
• AD_FORMAT_UNORM_INT8X1 - 1 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT8X2 - 2 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT8X4 - 4 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT16X1 - 1 channel unsigned 16-bit normalized integer
• AD_FORMAT_UNORM_INT16X2 - 2 channel unsigned 16-bit normalized integer
• AD_FORMAT_UNORM_INT16X4 - 4 channel unsigned 16-bit normalized integer
• AD_FORMAT_SNORM_INT8X1 - 1 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT8X2 - 2 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT8X4 - 4 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT16X1 - 1 channel signed 16-bit normalized integer
• AD_FORMAT_SNORM_INT16X2 - 2 channel signed 16-bit normalized integer
• AD_FORMAT_SNORM_INT16X4 - 4 channel signed 16-bit normalized integer
• AD_FORMAT_BC1_UNORM - 4 channel unsigned normalized block-compressed (BC1 compression) format
• AD_FORMAT_BC1_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC1 compression) format with sRGB encoding
• AD_FORMAT_BC2_UNORM - 4 channel unsigned normalized block-compressed (BC2 compression) format
• AD_FORMAT_BC2_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC2 compression) format with sRGB encoding
• AD_FORMAT_BC3_UNORM - 4 channel unsigned normalized block-compressed (BC3 compression) format
• AD_FORMAT_BC3_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC3 compression) format with sRGB encoding
• AD_FORMAT_BC4_UNORM - 1 channel unsigned normalized block-compressed (BC4 compression) format
• AD_FORMAT_BC4_SNORM - 1 channel signed normalized block-compressed (BC4 compression) format
• AD_FORMAT_BC5_UNORM - 2 channel unsigned normalized block-compressed (BC5 compression) format
• AD_FORMAT_BC5_SNORM - 2 channel signed normalized block-compressed (BC5 compression) format
• AD_FORMAT_BC6H_UF16 - 3 channel unsigned half-float block-compressed (BC6H compression) format
• AD_FORMAT_BC6H_SF16 - 3 channel signed half-float block-compressed (BC6H compression) format
• AD_FORMAT_BC7_UNORM - 4 channel unsigned normalized block-compressed (BC7 compression) format
• AD_FORMAT_BC7_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC7 compression) format with sRGB encoding

See Also:

• Constant Field Values

CU_AD_FORMAT_SNORM_INT8X2

public static final int CU_AD_FORMAT_SNORM_INT8X2

Array formats. (CUarray_format)

Enum values:

• AD_FORMAT_UNSIGNED_INT8 - Unsigned 8-bit integers
• AD_FORMAT_UNSIGNED_INT16 - Unsigned 16-bit integers
• AD_FORMAT_UNSIGNED_INT32 - Unsigned 32-bit integers
• AD_FORMAT_SIGNED_INT8 - Signed 8-bit integers
• AD_FORMAT_SIGNED_INT16 - Signed 16-bit integers
• AD_FORMAT_SIGNED_INT32 - Signed 32-bit integers
• AD_FORMAT_HALF - 16-bit floating point
• AD_FORMAT_FLOAT - 32-bit floating point
• AD_FORMAT_NV12 - 8-bit YUV planar format, with 4:2:0 sampling
• AD_FORMAT_UNORM_INT8X1 - 1 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT8X2 - 2 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT8X4 - 4 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT16X1 - 1 channel unsigned 16-bit normalized integer
• AD_FORMAT_UNORM_INT16X2 - 2 channel unsigned 16-bit normalized integer
• AD_FORMAT_UNORM_INT16X4 - 4 channel unsigned 16-bit normalized integer
• AD_FORMAT_SNORM_INT8X1 - 1 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT8X2 - 2 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT8X4 - 4 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT16X1 - 1 channel signed 16-bit normalized integer
• AD_FORMAT_SNORM_INT16X2 - 2 channel signed 16-bit normalized integer
• AD_FORMAT_SNORM_INT16X4 - 4 channel signed 16-bit normalized integer
• AD_FORMAT_BC1_UNORM - 4 channel unsigned normalized block-compressed (BC1 compression) format
• AD_FORMAT_BC1_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC1 compression) format with sRGB encoding
• AD_FORMAT_BC2_UNORM - 4 channel unsigned normalized block-compressed (BC2 compression) format
• AD_FORMAT_BC2_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC2 compression) format with sRGB encoding
• AD_FORMAT_BC3_UNORM - 4 channel unsigned normalized block-compressed (BC3 compression) format
• AD_FORMAT_BC3_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC3 compression) format with sRGB encoding
• AD_FORMAT_BC4_UNORM - 1 channel unsigned normalized block-compressed (BC4 compression) format
• AD_FORMAT_BC4_SNORM - 1 channel signed normalized block-compressed (BC4 compression) format
• AD_FORMAT_BC5_UNORM - 2 channel unsigned normalized block-compressed (BC5 compression) format
• AD_FORMAT_BC5_SNORM - 2 channel signed normalized block-compressed (BC5 compression) format
• AD_FORMAT_BC6H_UF16 - 3 channel unsigned half-float block-compressed (BC6H compression) format
• AD_FORMAT_BC6H_SF16 - 3 channel signed half-float block-compressed (BC6H compression) format
• AD_FORMAT_BC7_UNORM - 4 channel unsigned normalized block-compressed (BC7 compression) format
• AD_FORMAT_BC7_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC7 compression) format with sRGB encoding

See Also:

• Constant Field Values

CU_AD_FORMAT_SNORM_INT8X4

public static final int CU_AD_FORMAT_SNORM_INT8X4

Array formats. (CUarray_format)

Enum values:

• AD_FORMAT_UNSIGNED_INT8 - Unsigned 8-bit integers
• AD_FORMAT_UNSIGNED_INT16 - Unsigned 16-bit integers
• AD_FORMAT_UNSIGNED_INT32 - Unsigned 32-bit integers
• AD_FORMAT_SIGNED_INT8 - Signed 8-bit integers
• AD_FORMAT_SIGNED_INT16 - Signed 16-bit integers
• AD_FORMAT_SIGNED_INT32 - Signed 32-bit integers
• AD_FORMAT_HALF - 16-bit floating point
• AD_FORMAT_FLOAT - 32-bit floating point
• AD_FORMAT_NV12 - 8-bit YUV planar format, with 4:2:0 sampling
• AD_FORMAT_UNORM_INT8X1 - 1 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT8X2 - 2 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT8X4 - 4 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT16X1 - 1 channel unsigned 16-bit normalized integer
• AD_FORMAT_UNORM_INT16X2 - 2 channel unsigned 16-bit normalized integer
• AD_FORMAT_UNORM_INT16X4 - 4 channel unsigned 16-bit normalized integer
• AD_FORMAT_SNORM_INT8X1 - 1 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT8X2 - 2 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT8X4 - 4 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT16X1 - 1 channel signed 16-bit normalized integer
• AD_FORMAT_SNORM_INT16X2 - 2 channel signed 16-bit normalized integer
• AD_FORMAT_SNORM_INT16X4 - 4 channel signed 16-bit normalized integer
• AD_FORMAT_BC1_UNORM - 4 channel unsigned normalized block-compressed (BC1 compression) format
• AD_FORMAT_BC1_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC1 compression) format with sRGB encoding
• AD_FORMAT_BC2_UNORM - 4 channel unsigned normalized block-compressed (BC2 compression) format
• AD_FORMAT_BC2_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC2 compression) format with sRGB encoding
• AD_FORMAT_BC3_UNORM - 4 channel unsigned normalized block-compressed (BC3 compression) format
• AD_FORMAT_BC3_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC3 compression) format with sRGB encoding
• AD_FORMAT_BC4_UNORM - 1 channel unsigned normalized block-compressed (BC4 compression) format
• AD_FORMAT_BC4_SNORM - 1 channel signed normalized block-compressed (BC4 compression) format
• AD_FORMAT_BC5_UNORM - 2 channel unsigned normalized block-compressed (BC5 compression) format
• AD_FORMAT_BC5_SNORM - 2 channel signed normalized block-compressed (BC5 compression) format
• AD_FORMAT_BC6H_UF16 - 3 channel unsigned half-float block-compressed (BC6H compression) format
• AD_FORMAT_BC6H_SF16 - 3 channel signed half-float block-compressed (BC6H compression) format
• AD_FORMAT_BC7_UNORM - 4 channel unsigned normalized block-compressed (BC7 compression) format
• AD_FORMAT_BC7_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC7 compression) format with sRGB encoding

See Also:

• Constant Field Values

CU_AD_FORMAT_SNORM_INT16X1

public static final int CU_AD_FORMAT_SNORM_INT16X1

Array formats. (CUarray_format)

Enum values:

• AD_FORMAT_UNSIGNED_INT8 - Unsigned 8-bit integers
• AD_FORMAT_UNSIGNED_INT16 - Unsigned 16-bit integers
• AD_FORMAT_UNSIGNED_INT32 - Unsigned 32-bit integers
• AD_FORMAT_SIGNED_INT8 - Signed 8-bit integers
• AD_FORMAT_SIGNED_INT16 - Signed 16-bit integers
• AD_FORMAT_SIGNED_INT32 - Signed 32-bit integers
• AD_FORMAT_HALF - 16-bit floating point
• AD_FORMAT_FLOAT - 32-bit floating point
• AD_FORMAT_NV12 - 8-bit YUV planar format, with 4:2:0 sampling
• AD_FORMAT_UNORM_INT8X1 - 1 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT8X2 - 2 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT8X4 - 4 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT16X1 - 1 channel unsigned 16-bit normalized integer
• AD_FORMAT_UNORM_INT16X2 - 2 channel unsigned 16-bit normalized integer
• AD_FORMAT_UNORM_INT16X4 - 4 channel unsigned 16-bit normalized integer
• AD_FORMAT_SNORM_INT8X1 - 1 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT8X2 - 2 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT8X4 - 4 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT16X1 - 1 channel signed 16-bit normalized integer
• AD_FORMAT_SNORM_INT16X2 - 2 channel signed 16-bit normalized integer
• AD_FORMAT_SNORM_INT16X4 - 4 channel signed 16-bit normalized integer
• AD_FORMAT_BC1_UNORM - 4 channel unsigned normalized block-compressed (BC1 compression) format
• AD_FORMAT_BC1_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC1 compression) format with sRGB encoding
• AD_FORMAT_BC2_UNORM - 4 channel unsigned normalized block-compressed (BC2 compression) format
• AD_FORMAT_BC2_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC2 compression) format with sRGB encoding
• AD_FORMAT_BC3_UNORM - 4 channel unsigned normalized block-compressed (BC3 compression) format
• AD_FORMAT_BC3_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC3 compression) format with sRGB encoding
• AD_FORMAT_BC4_UNORM - 1 channel unsigned normalized block-compressed (BC4 compression) format
• AD_FORMAT_BC4_SNORM - 1 channel signed normalized block-compressed (BC4 compression) format
• AD_FORMAT_BC5_UNORM - 2 channel unsigned normalized block-compressed (BC5 compression) format
• AD_FORMAT_BC5_SNORM - 2 channel signed normalized block-compressed (BC5 compression) format
• AD_FORMAT_BC6H_UF16 - 3 channel unsigned half-float block-compressed (BC6H compression) format
• AD_FORMAT_BC6H_SF16 - 3 channel signed half-float block-compressed (BC6H compression) format
• AD_FORMAT_BC7_UNORM - 4 channel unsigned normalized block-compressed (BC7 compression) format
• AD_FORMAT_BC7_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC7 compression) format with sRGB encoding

See Also:

• Constant Field Values

CU_AD_FORMAT_SNORM_INT16X2

public static final int CU_AD_FORMAT_SNORM_INT16X2

Array formats. (CUarray_format)

Enum values:

• AD_FORMAT_UNSIGNED_INT8 - Unsigned 8-bit integers
• AD_FORMAT_UNSIGNED_INT16 - Unsigned 16-bit integers
• AD_FORMAT_UNSIGNED_INT32 - Unsigned 32-bit integers
• AD_FORMAT_SIGNED_INT8 - Signed 8-bit integers
• AD_FORMAT_SIGNED_INT16 - Signed 16-bit integers
• AD_FORMAT_SIGNED_INT32 - Signed 32-bit integers
• AD_FORMAT_HALF - 16-bit floating point
• AD_FORMAT_FLOAT - 32-bit floating point
• AD_FORMAT_NV12 - 8-bit YUV planar format, with 4:2:0 sampling
• AD_FORMAT_UNORM_INT8X1 - 1 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT8X2 - 2 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT8X4 - 4 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT16X1 - 1 channel unsigned 16-bit normalized integer
• AD_FORMAT_UNORM_INT16X2 - 2 channel unsigned 16-bit normalized integer
• AD_FORMAT_UNORM_INT16X4 - 4 channel unsigned 16-bit normalized integer
• AD_FORMAT_SNORM_INT8X1 - 1 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT8X2 - 2 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT8X4 - 4 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT16X1 - 1 channel signed 16-bit normalized integer
• AD_FORMAT_SNORM_INT16X2 - 2 channel signed 16-bit normalized integer
• AD_FORMAT_SNORM_INT16X4 - 4 channel signed 16-bit normalized integer
• AD_FORMAT_BC1_UNORM - 4 channel unsigned normalized block-compressed (BC1 compression) format
• AD_FORMAT_BC1_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC1 compression) format with sRGB encoding
• AD_FORMAT_BC2_UNORM - 4 channel unsigned normalized block-compressed (BC2 compression) format
• AD_FORMAT_BC2_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC2 compression) format with sRGB encoding
• AD_FORMAT_BC3_UNORM - 4 channel unsigned normalized block-compressed (BC3 compression) format
• AD_FORMAT_BC3_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC3 compression) format with sRGB encoding
• AD_FORMAT_BC4_UNORM - 1 channel unsigned normalized block-compressed (BC4 compression) format
• AD_FORMAT_BC4_SNORM - 1 channel signed normalized block-compressed (BC4 compression) format
• AD_FORMAT_BC5_UNORM - 2 channel unsigned normalized block-compressed (BC5 compression) format
• AD_FORMAT_BC5_SNORM - 2 channel signed normalized block-compressed (BC5 compression) format
• AD_FORMAT_BC6H_UF16 - 3 channel unsigned half-float block-compressed (BC6H compression) format
• AD_FORMAT_BC6H_SF16 - 3 channel signed half-float block-compressed (BC6H compression) format
• AD_FORMAT_BC7_UNORM - 4 channel unsigned normalized block-compressed (BC7 compression) format
• AD_FORMAT_BC7_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC7 compression) format with sRGB encoding

See Also:

• Constant Field Values

CU_AD_FORMAT_SNORM_INT16X4

public static final int CU_AD_FORMAT_SNORM_INT16X4

Array formats. (CUarray_format)

Enum values:

• AD_FORMAT_UNSIGNED_INT8 - Unsigned 8-bit integers
• AD_FORMAT_UNSIGNED_INT16 - Unsigned 16-bit integers
• AD_FORMAT_UNSIGNED_INT32 - Unsigned 32-bit integers
• AD_FORMAT_SIGNED_INT8 - Signed 8-bit integers
• AD_FORMAT_SIGNED_INT16 - Signed 16-bit integers
• AD_FORMAT_SIGNED_INT32 - Signed 32-bit integers
• AD_FORMAT_HALF - 16-bit floating point
• AD_FORMAT_FLOAT - 32-bit floating point
• AD_FORMAT_NV12 - 8-bit YUV planar format, with 4:2:0 sampling
• AD_FORMAT_UNORM_INT8X1 - 1 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT8X2 - 2 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT8X4 - 4 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT16X1 - 1 channel unsigned 16-bit normalized integer
• AD_FORMAT_UNORM_INT16X2 - 2 channel unsigned 16-bit normalized integer
• AD_FORMAT_UNORM_INT16X4 - 4 channel unsigned 16-bit normalized integer
• AD_FORMAT_SNORM_INT8X1 - 1 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT8X2 - 2 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT8X4 - 4 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT16X1 - 1 channel signed 16-bit normalized integer
• AD_FORMAT_SNORM_INT16X2 - 2 channel signed 16-bit normalized integer
• AD_FORMAT_SNORM_INT16X4 - 4 channel signed 16-bit normalized integer
• AD_FORMAT_BC1_UNORM - 4 channel unsigned normalized block-compressed (BC1 compression) format
• AD_FORMAT_BC1_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC1 compression) format with sRGB encoding
• AD_FORMAT_BC2_UNORM - 4 channel unsigned normalized block-compressed (BC2 compression) format
• AD_FORMAT_BC2_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC2 compression) format with sRGB encoding
• AD_FORMAT_BC3_UNORM - 4 channel unsigned normalized block-compressed (BC3 compression) format
• AD_FORMAT_BC3_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC3 compression) format with sRGB encoding
• AD_FORMAT_BC4_UNORM - 1 channel unsigned normalized block-compressed (BC4 compression) format
• AD_FORMAT_BC4_SNORM - 1 channel signed normalized block-compressed (BC4 compression) format
• AD_FORMAT_BC5_UNORM - 2 channel unsigned normalized block-compressed (BC5 compression) format
• AD_FORMAT_BC5_SNORM - 2 channel signed normalized block-compressed (BC5 compression) format
• AD_FORMAT_BC6H_UF16 - 3 channel unsigned half-float block-compressed (BC6H compression) format
• AD_FORMAT_BC6H_SF16 - 3 channel signed half-float block-compressed (BC6H compression) format
• AD_FORMAT_BC7_UNORM - 4 channel unsigned normalized block-compressed (BC7 compression) format
• AD_FORMAT_BC7_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC7 compression) format with sRGB encoding

See Also:

• Constant Field Values

CU_AD_FORMAT_BC1_UNORM

public static final int CU_AD_FORMAT_BC1_UNORM

Array formats. (CUarray_format)

Enum values:

• AD_FORMAT_UNSIGNED_INT8 - Unsigned 8-bit integers
• AD_FORMAT_UNSIGNED_INT16 - Unsigned 16-bit integers
• AD_FORMAT_UNSIGNED_INT32 - Unsigned 32-bit integers
• AD_FORMAT_SIGNED_INT8 - Signed 8-bit integers
• AD_FORMAT_SIGNED_INT16 - Signed 16-bit integers
• AD_FORMAT_SIGNED_INT32 - Signed 32-bit integers
• AD_FORMAT_HALF - 16-bit floating point
• AD_FORMAT_FLOAT - 32-bit floating point
• AD_FORMAT_NV12 - 8-bit YUV planar format, with 4:2:0 sampling
• AD_FORMAT_UNORM_INT8X1 - 1 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT8X2 - 2 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT8X4 - 4 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT16X1 - 1 channel unsigned 16-bit normalized integer
• AD_FORMAT_UNORM_INT16X2 - 2 channel unsigned 16-bit normalized integer
• AD_FORMAT_UNORM_INT16X4 - 4 channel unsigned 16-bit normalized integer
• AD_FORMAT_SNORM_INT8X1 - 1 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT8X2 - 2 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT8X4 - 4 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT16X1 - 1 channel signed 16-bit normalized integer
• AD_FORMAT_SNORM_INT16X2 - 2 channel signed 16-bit normalized integer
• AD_FORMAT_SNORM_INT16X4 - 4 channel signed 16-bit normalized integer
• AD_FORMAT_BC1_UNORM - 4 channel unsigned normalized block-compressed (BC1 compression) format
• AD_FORMAT_BC1_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC1 compression) format with sRGB encoding
• AD_FORMAT_BC2_UNORM - 4 channel unsigned normalized block-compressed (BC2 compression) format
• AD_FORMAT_BC2_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC2 compression) format with sRGB encoding
• AD_FORMAT_BC3_UNORM - 4 channel unsigned normalized block-compressed (BC3 compression) format
• AD_FORMAT_BC3_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC3 compression) format with sRGB encoding
• AD_FORMAT_BC4_UNORM - 1 channel unsigned normalized block-compressed (BC4 compression) format
• AD_FORMAT_BC4_SNORM - 1 channel signed normalized block-compressed (BC4 compression) format
• AD_FORMAT_BC5_UNORM - 2 channel unsigned normalized block-compressed (BC5 compression) format
• AD_FORMAT_BC5_SNORM - 2 channel signed normalized block-compressed (BC5 compression) format
• AD_FORMAT_BC6H_UF16 - 3 channel unsigned half-float block-compressed (BC6H compression) format
• AD_FORMAT_BC6H_SF16 - 3 channel signed half-float block-compressed (BC6H compression) format
• AD_FORMAT_BC7_UNORM - 4 channel unsigned normalized block-compressed (BC7 compression) format
• AD_FORMAT_BC7_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC7 compression) format with sRGB encoding

See Also:

• Constant Field Values

CU_AD_FORMAT_BC1_UNORM_SRGB

public static final int CU_AD_FORMAT_BC1_UNORM_SRGB

Array formats. (CUarray_format)

Enum values:

• AD_FORMAT_UNSIGNED_INT8 - Unsigned 8-bit integers
• AD_FORMAT_UNSIGNED_INT16 - Unsigned 16-bit integers
• AD_FORMAT_UNSIGNED_INT32 - Unsigned 32-bit integers
• AD_FORMAT_SIGNED_INT8 - Signed 8-bit integers
• AD_FORMAT_SIGNED_INT16 - Signed 16-bit integers
• AD_FORMAT_SIGNED_INT32 - Signed 32-bit integers
• AD_FORMAT_HALF - 16-bit floating point
• AD_FORMAT_FLOAT - 32-bit floating point
• AD_FORMAT_NV12 - 8-bit YUV planar format, with 4:2:0 sampling
• AD_FORMAT_UNORM_INT8X1 - 1 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT8X2 - 2 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT8X4 - 4 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT16X1 - 1 channel unsigned 16-bit normalized integer
• AD_FORMAT_UNORM_INT16X2 - 2 channel unsigned 16-bit normalized integer
• AD_FORMAT_UNORM_INT16X4 - 4 channel unsigned 16-bit normalized integer
• AD_FORMAT_SNORM_INT8X1 - 1 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT8X2 - 2 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT8X4 - 4 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT16X1 - 1 channel signed 16-bit normalized integer
• AD_FORMAT_SNORM_INT16X2 - 2 channel signed 16-bit normalized integer
• AD_FORMAT_SNORM_INT16X4 - 4 channel signed 16-bit normalized integer
• AD_FORMAT_BC1_UNORM - 4 channel unsigned normalized block-compressed (BC1 compression) format
• AD_FORMAT_BC1_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC1 compression) format with sRGB encoding
• AD_FORMAT_BC2_UNORM - 4 channel unsigned normalized block-compressed (BC2 compression) format
• AD_FORMAT_BC2_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC2 compression) format with sRGB encoding
• AD_FORMAT_BC3_UNORM - 4 channel unsigned normalized block-compressed (BC3 compression) format
• AD_FORMAT_BC3_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC3 compression) format with sRGB encoding
• AD_FORMAT_BC4_UNORM - 1 channel unsigned normalized block-compressed (BC4 compression) format
• AD_FORMAT_BC4_SNORM - 1 channel signed normalized block-compressed (BC4 compression) format
• AD_FORMAT_BC5_UNORM - 2 channel unsigned normalized block-compressed (BC5 compression) format
• AD_FORMAT_BC5_SNORM - 2 channel signed normalized block-compressed (BC5 compression) format
• AD_FORMAT_BC6H_UF16 - 3 channel unsigned half-float block-compressed (BC6H compression) format
• AD_FORMAT_BC6H_SF16 - 3 channel signed half-float block-compressed (BC6H compression) format
• AD_FORMAT_BC7_UNORM - 4 channel unsigned normalized block-compressed (BC7 compression) format
• AD_FORMAT_BC7_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC7 compression) format with sRGB encoding

See Also:

• Constant Field Values

CU_AD_FORMAT_BC2_UNORM

public static final int CU_AD_FORMAT_BC2_UNORM

Array formats. (CUarray_format)

Enum values:

• AD_FORMAT_UNSIGNED_INT8 - Unsigned 8-bit integers
• AD_FORMAT_UNSIGNED_INT16 - Unsigned 16-bit integers
• AD_FORMAT_UNSIGNED_INT32 - Unsigned 32-bit integers
• AD_FORMAT_SIGNED_INT8 - Signed 8-bit integers
• AD_FORMAT_SIGNED_INT16 - Signed 16-bit integers
• AD_FORMAT_SIGNED_INT32 - Signed 32-bit integers
• AD_FORMAT_HALF - 16-bit floating point
• AD_FORMAT_FLOAT - 32-bit floating point
• AD_FORMAT_NV12 - 8-bit YUV planar format, with 4:2:0 sampling
• AD_FORMAT_UNORM_INT8X1 - 1 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT8X2 - 2 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT8X4 - 4 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT16X1 - 1 channel unsigned 16-bit normalized integer
• AD_FORMAT_UNORM_INT16X2 - 2 channel unsigned 16-bit normalized integer
• AD_FORMAT_UNORM_INT16X4 - 4 channel unsigned 16-bit normalized integer
• AD_FORMAT_SNORM_INT8X1 - 1 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT8X2 - 2 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT8X4 - 4 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT16X1 - 1 channel signed 16-bit normalized integer
• AD_FORMAT_SNORM_INT16X2 - 2 channel signed 16-bit normalized integer
• AD_FORMAT_SNORM_INT16X4 - 4 channel signed 16-bit normalized integer
• AD_FORMAT_BC1_UNORM - 4 channel unsigned normalized block-compressed (BC1 compression) format
• AD_FORMAT_BC1_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC1 compression) format with sRGB encoding
• AD_FORMAT_BC2_UNORM - 4 channel unsigned normalized block-compressed (BC2 compression) format
• AD_FORMAT_BC2_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC2 compression) format with sRGB encoding
• AD_FORMAT_BC3_UNORM - 4 channel unsigned normalized block-compressed (BC3 compression) format
• AD_FORMAT_BC3_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC3 compression) format with sRGB encoding
• AD_FORMAT_BC4_UNORM - 1 channel unsigned normalized block-compressed (BC4 compression) format
• AD_FORMAT_BC4_SNORM - 1 channel signed normalized block-compressed (BC4 compression) format
• AD_FORMAT_BC5_UNORM - 2 channel unsigned normalized block-compressed (BC5 compression) format
• AD_FORMAT_BC5_SNORM - 2 channel signed normalized block-compressed (BC5 compression) format
• AD_FORMAT_BC6H_UF16 - 3 channel unsigned half-float block-compressed (BC6H compression) format
• AD_FORMAT_BC6H_SF16 - 3 channel signed half-float block-compressed (BC6H compression) format
• AD_FORMAT_BC7_UNORM - 4 channel unsigned normalized block-compressed (BC7 compression) format
• AD_FORMAT_BC7_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC7 compression) format with sRGB encoding

See Also:

• Constant Field Values

CU_AD_FORMAT_BC2_UNORM_SRGB

public static final int CU_AD_FORMAT_BC2_UNORM_SRGB

Array formats. (CUarray_format)

Enum values:

• AD_FORMAT_UNSIGNED_INT8 - Unsigned 8-bit integers
• AD_FORMAT_UNSIGNED_INT16 - Unsigned 16-bit integers
• AD_FORMAT_UNSIGNED_INT32 - Unsigned 32-bit integers
• AD_FORMAT_SIGNED_INT8 - Signed 8-bit integers
• AD_FORMAT_SIGNED_INT16 - Signed 16-bit integers
• AD_FORMAT_SIGNED_INT32 - Signed 32-bit integers
• AD_FORMAT_HALF - 16-bit floating point
• AD_FORMAT_FLOAT - 32-bit floating point
• AD_FORMAT_NV12 - 8-bit YUV planar format, with 4:2:0 sampling
• AD_FORMAT_UNORM_INT8X1 - 1 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT8X2 - 2 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT8X4 - 4 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT16X1 - 1 channel unsigned 16-bit normalized integer
• AD_FORMAT_UNORM_INT16X2 - 2 channel unsigned 16-bit normalized integer
• AD_FORMAT_UNORM_INT16X4 - 4 channel unsigned 16-bit normalized integer
• AD_FORMAT_SNORM_INT8X1 - 1 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT8X2 - 2 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT8X4 - 4 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT16X1 - 1 channel signed 16-bit normalized integer
• AD_FORMAT_SNORM_INT16X2 - 2 channel signed 16-bit normalized integer
• AD_FORMAT_SNORM_INT16X4 - 4 channel signed 16-bit normalized integer
• AD_FORMAT_BC1_UNORM - 4 channel unsigned normalized block-compressed (BC1 compression) format
• AD_FORMAT_BC1_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC1 compression) format with sRGB encoding
• AD_FORMAT_BC2_UNORM - 4 channel unsigned normalized block-compressed (BC2 compression) format
• AD_FORMAT_BC2_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC2 compression) format with sRGB encoding
• AD_FORMAT_BC3_UNORM - 4 channel unsigned normalized block-compressed (BC3 compression) format
• AD_FORMAT_BC3_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC3 compression) format with sRGB encoding
• AD_FORMAT_BC4_UNORM - 1 channel unsigned normalized block-compressed (BC4 compression) format
• AD_FORMAT_BC4_SNORM - 1 channel signed normalized block-compressed (BC4 compression) format
• AD_FORMAT_BC5_UNORM - 2 channel unsigned normalized block-compressed (BC5 compression) format
• AD_FORMAT_BC5_SNORM - 2 channel signed normalized block-compressed (BC5 compression) format
• AD_FORMAT_BC6H_UF16 - 3 channel unsigned half-float block-compressed (BC6H compression) format
• AD_FORMAT_BC6H_SF16 - 3 channel signed half-float block-compressed (BC6H compression) format
• AD_FORMAT_BC7_UNORM - 4 channel unsigned normalized block-compressed (BC7 compression) format
• AD_FORMAT_BC7_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC7 compression) format with sRGB encoding

See Also:

• Constant Field Values

CU_AD_FORMAT_BC3_UNORM

public static final int CU_AD_FORMAT_BC3_UNORM

Array formats. (CUarray_format)

Enum values:

• AD_FORMAT_UNSIGNED_INT8 - Unsigned 8-bit integers
• AD_FORMAT_UNSIGNED_INT16 - Unsigned 16-bit integers
• AD_FORMAT_UNSIGNED_INT32 - Unsigned 32-bit integers
• AD_FORMAT_SIGNED_INT8 - Signed 8-bit integers
• AD_FORMAT_SIGNED_INT16 - Signed 16-bit integers
• AD_FORMAT_SIGNED_INT32 - Signed 32-bit integers
• AD_FORMAT_HALF - 16-bit floating point
• AD_FORMAT_FLOAT - 32-bit floating point
• AD_FORMAT_NV12 - 8-bit YUV planar format, with 4:2:0 sampling
• AD_FORMAT_UNORM_INT8X1 - 1 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT8X2 - 2 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT8X4 - 4 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT16X1 - 1 channel unsigned 16-bit normalized integer
• AD_FORMAT_UNORM_INT16X2 - 2 channel unsigned 16-bit normalized integer
• AD_FORMAT_UNORM_INT16X4 - 4 channel unsigned 16-bit normalized integer
• AD_FORMAT_SNORM_INT8X1 - 1 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT8X2 - 2 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT8X4 - 4 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT16X1 - 1 channel signed 16-bit normalized integer
• AD_FORMAT_SNORM_INT16X2 - 2 channel signed 16-bit normalized integer
• AD_FORMAT_SNORM_INT16X4 - 4 channel signed 16-bit normalized integer
• AD_FORMAT_BC1_UNORM - 4 channel unsigned normalized block-compressed (BC1 compression) format
• AD_FORMAT_BC1_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC1 compression) format with sRGB encoding
• AD_FORMAT_BC2_UNORM - 4 channel unsigned normalized block-compressed (BC2 compression) format
• AD_FORMAT_BC2_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC2 compression) format with sRGB encoding
• AD_FORMAT_BC3_UNORM - 4 channel unsigned normalized block-compressed (BC3 compression) format
• AD_FORMAT_BC3_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC3 compression) format with sRGB encoding
• AD_FORMAT_BC4_UNORM - 1 channel unsigned normalized block-compressed (BC4 compression) format
• AD_FORMAT_BC4_SNORM - 1 channel signed normalized block-compressed (BC4 compression) format
• AD_FORMAT_BC5_UNORM - 2 channel unsigned normalized block-compressed (BC5 compression) format
• AD_FORMAT_BC5_SNORM - 2 channel signed normalized block-compressed (BC5 compression) format
• AD_FORMAT_BC6H_UF16 - 3 channel unsigned half-float block-compressed (BC6H compression) format
• AD_FORMAT_BC6H_SF16 - 3 channel signed half-float block-compressed (BC6H compression) format
• AD_FORMAT_BC7_UNORM - 4 channel unsigned normalized block-compressed (BC7 compression) format
• AD_FORMAT_BC7_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC7 compression) format with sRGB encoding

See Also:

• Constant Field Values

CU_AD_FORMAT_BC3_UNORM_SRGB

public static final int CU_AD_FORMAT_BC3_UNORM_SRGB

Array formats. (CUarray_format)

Enum values:

• AD_FORMAT_UNSIGNED_INT8 - Unsigned 8-bit integers
• AD_FORMAT_UNSIGNED_INT16 - Unsigned 16-bit integers
• AD_FORMAT_UNSIGNED_INT32 - Unsigned 32-bit integers
• AD_FORMAT_SIGNED_INT8 - Signed 8-bit integers
• AD_FORMAT_SIGNED_INT16 - Signed 16-bit integers
• AD_FORMAT_SIGNED_INT32 - Signed 32-bit integers
• AD_FORMAT_HALF - 16-bit floating point
• AD_FORMAT_FLOAT - 32-bit floating point
• AD_FORMAT_NV12 - 8-bit YUV planar format, with 4:2:0 sampling
• AD_FORMAT_UNORM_INT8X1 - 1 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT8X2 - 2 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT8X4 - 4 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT16X1 - 1 channel unsigned 16-bit normalized integer
• AD_FORMAT_UNORM_INT16X2 - 2 channel unsigned 16-bit normalized integer
• AD_FORMAT_UNORM_INT16X4 - 4 channel unsigned 16-bit normalized integer
• AD_FORMAT_SNORM_INT8X1 - 1 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT8X2 - 2 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT8X4 - 4 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT16X1 - 1 channel signed 16-bit normalized integer
• AD_FORMAT_SNORM_INT16X2 - 2 channel signed 16-bit normalized integer
• AD_FORMAT_SNORM_INT16X4 - 4 channel signed 16-bit normalized integer
• AD_FORMAT_BC1_UNORM - 4 channel unsigned normalized block-compressed (BC1 compression) format
• AD_FORMAT_BC1_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC1 compression) format with sRGB encoding
• AD_FORMAT_BC2_UNORM - 4 channel unsigned normalized block-compressed (BC2 compression) format
• AD_FORMAT_BC2_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC2 compression) format with sRGB encoding
• AD_FORMAT_BC3_UNORM - 4 channel unsigned normalized block-compressed (BC3 compression) format
• AD_FORMAT_BC3_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC3 compression) format with sRGB encoding
• AD_FORMAT_BC4_UNORM - 1 channel unsigned normalized block-compressed (BC4 compression) format
• AD_FORMAT_BC4_SNORM - 1 channel signed normalized block-compressed (BC4 compression) format
• AD_FORMAT_BC5_UNORM - 2 channel unsigned normalized block-compressed (BC5 compression) format
• AD_FORMAT_BC5_SNORM - 2 channel signed normalized block-compressed (BC5 compression) format
• AD_FORMAT_BC6H_UF16 - 3 channel unsigned half-float block-compressed (BC6H compression) format
• AD_FORMAT_BC6H_SF16 - 3 channel signed half-float block-compressed (BC6H compression) format
• AD_FORMAT_BC7_UNORM - 4 channel unsigned normalized block-compressed (BC7 compression) format
• AD_FORMAT_BC7_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC7 compression) format with sRGB encoding

See Also:

• Constant Field Values

CU_AD_FORMAT_BC4_UNORM

public static final int CU_AD_FORMAT_BC4_UNORM

Array formats. (CUarray_format)

Enum values:

• AD_FORMAT_UNSIGNED_INT8 - Unsigned 8-bit integers
• AD_FORMAT_UNSIGNED_INT16 - Unsigned 16-bit integers
• AD_FORMAT_UNSIGNED_INT32 - Unsigned 32-bit integers
• AD_FORMAT_SIGNED_INT8 - Signed 8-bit integers
• AD_FORMAT_SIGNED_INT16 - Signed 16-bit integers
• AD_FORMAT_SIGNED_INT32 - Signed 32-bit integers
• AD_FORMAT_HALF - 16-bit floating point
• AD_FORMAT_FLOAT - 32-bit floating point
• AD_FORMAT_NV12 - 8-bit YUV planar format, with 4:2:0 sampling
• AD_FORMAT_UNORM_INT8X1 - 1 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT8X2 - 2 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT8X4 - 4 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT16X1 - 1 channel unsigned 16-bit normalized integer
• AD_FORMAT_UNORM_INT16X2 - 2 channel unsigned 16-bit normalized integer
• AD_FORMAT_UNORM_INT16X4 - 4 channel unsigned 16-bit normalized integer
• AD_FORMAT_SNORM_INT8X1 - 1 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT8X2 - 2 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT8X4 - 4 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT16X1 - 1 channel signed 16-bit normalized integer
• AD_FORMAT_SNORM_INT16X2 - 2 channel signed 16-bit normalized integer
• AD_FORMAT_SNORM_INT16X4 - 4 channel signed 16-bit normalized integer
• AD_FORMAT_BC1_UNORM - 4 channel unsigned normalized block-compressed (BC1 compression) format
• AD_FORMAT_BC1_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC1 compression) format with sRGB encoding
• AD_FORMAT_BC2_UNORM - 4 channel unsigned normalized block-compressed (BC2 compression) format
• AD_FORMAT_BC2_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC2 compression) format with sRGB encoding
• AD_FORMAT_BC3_UNORM - 4 channel unsigned normalized block-compressed (BC3 compression) format
• AD_FORMAT_BC3_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC3 compression) format with sRGB encoding
• AD_FORMAT_BC4_UNORM - 1 channel unsigned normalized block-compressed (BC4 compression) format
• AD_FORMAT_BC4_SNORM - 1 channel signed normalized block-compressed (BC4 compression) format
• AD_FORMAT_BC5_UNORM - 2 channel unsigned normalized block-compressed (BC5 compression) format
• AD_FORMAT_BC5_SNORM - 2 channel signed normalized block-compressed (BC5 compression) format
• AD_FORMAT_BC6H_UF16 - 3 channel unsigned half-float block-compressed (BC6H compression) format
• AD_FORMAT_BC6H_SF16 - 3 channel signed half-float block-compressed (BC6H compression) format
• AD_FORMAT_BC7_UNORM - 4 channel unsigned normalized block-compressed (BC7 compression) format
• AD_FORMAT_BC7_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC7 compression) format with sRGB encoding

See Also:

• Constant Field Values

CU_AD_FORMAT_BC4_SNORM

public static final int CU_AD_FORMAT_BC4_SNORM

Array formats. (CUarray_format)

Enum values:

• AD_FORMAT_UNSIGNED_INT8 - Unsigned 8-bit integers
• AD_FORMAT_UNSIGNED_INT16 - Unsigned 16-bit integers
• AD_FORMAT_UNSIGNED_INT32 - Unsigned 32-bit integers
• AD_FORMAT_SIGNED_INT8 - Signed 8-bit integers
• AD_FORMAT_SIGNED_INT16 - Signed 16-bit integers
• AD_FORMAT_SIGNED_INT32 - Signed 32-bit integers
• AD_FORMAT_HALF - 16-bit floating point
• AD_FORMAT_FLOAT - 32-bit floating point
• AD_FORMAT_NV12 - 8-bit YUV planar format, with 4:2:0 sampling
• AD_FORMAT_UNORM_INT8X1 - 1 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT8X2 - 2 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT8X4 - 4 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT16X1 - 1 channel unsigned 16-bit normalized integer
• AD_FORMAT_UNORM_INT16X2 - 2 channel unsigned 16-bit normalized integer
• AD_FORMAT_UNORM_INT16X4 - 4 channel unsigned 16-bit normalized integer
• AD_FORMAT_SNORM_INT8X1 - 1 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT8X2 - 2 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT8X4 - 4 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT16X1 - 1 channel signed 16-bit normalized integer
• AD_FORMAT_SNORM_INT16X2 - 2 channel signed 16-bit normalized integer
• AD_FORMAT_SNORM_INT16X4 - 4 channel signed 16-bit normalized integer
• AD_FORMAT_BC1_UNORM - 4 channel unsigned normalized block-compressed (BC1 compression) format
• AD_FORMAT_BC1_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC1 compression) format with sRGB encoding
• AD_FORMAT_BC2_UNORM - 4 channel unsigned normalized block-compressed (BC2 compression) format
• AD_FORMAT_BC2_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC2 compression) format with sRGB encoding
• AD_FORMAT_BC3_UNORM - 4 channel unsigned normalized block-compressed (BC3 compression) format
• AD_FORMAT_BC3_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC3 compression) format with sRGB encoding
• AD_FORMAT_BC4_UNORM - 1 channel unsigned normalized block-compressed (BC4 compression) format
• AD_FORMAT_BC4_SNORM - 1 channel signed normalized block-compressed (BC4 compression) format
• AD_FORMAT_BC5_UNORM - 2 channel unsigned normalized block-compressed (BC5 compression) format
• AD_FORMAT_BC5_SNORM - 2 channel signed normalized block-compressed (BC5 compression) format
• AD_FORMAT_BC6H_UF16 - 3 channel unsigned half-float block-compressed (BC6H compression) format
• AD_FORMAT_BC6H_SF16 - 3 channel signed half-float block-compressed (BC6H compression) format
• AD_FORMAT_BC7_UNORM - 4 channel unsigned normalized block-compressed (BC7 compression) format
• AD_FORMAT_BC7_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC7 compression) format with sRGB encoding

See Also:

• Constant Field Values

CU_AD_FORMAT_BC5_UNORM

public static final int CU_AD_FORMAT_BC5_UNORM

Array formats. (CUarray_format)

Enum values:

• AD_FORMAT_UNSIGNED_INT8 - Unsigned 8-bit integers
• AD_FORMAT_UNSIGNED_INT16 - Unsigned 16-bit integers
• AD_FORMAT_UNSIGNED_INT32 - Unsigned 32-bit integers
• AD_FORMAT_SIGNED_INT8 - Signed 8-bit integers
• AD_FORMAT_SIGNED_INT16 - Signed 16-bit integers
• AD_FORMAT_SIGNED_INT32 - Signed 32-bit integers
• AD_FORMAT_HALF - 16-bit floating point
• AD_FORMAT_FLOAT - 32-bit floating point
• AD_FORMAT_NV12 - 8-bit YUV planar format, with 4:2:0 sampling
• AD_FORMAT_UNORM_INT8X1 - 1 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT8X2 - 2 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT8X4 - 4 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT16X1 - 1 channel unsigned 16-bit normalized integer
• AD_FORMAT_UNORM_INT16X2 - 2 channel unsigned 16-bit normalized integer
• AD_FORMAT_UNORM_INT16X4 - 4 channel unsigned 16-bit normalized integer
• AD_FORMAT_SNORM_INT8X1 - 1 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT8X2 - 2 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT8X4 - 4 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT16X1 - 1 channel signed 16-bit normalized integer
• AD_FORMAT_SNORM_INT16X2 - 2 channel signed 16-bit normalized integer
• AD_FORMAT_SNORM_INT16X4 - 4 channel signed 16-bit normalized integer
• AD_FORMAT_BC1_UNORM - 4 channel unsigned normalized block-compressed (BC1 compression) format
• AD_FORMAT_BC1_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC1 compression) format with sRGB encoding
• AD_FORMAT_BC2_UNORM - 4 channel unsigned normalized block-compressed (BC2 compression) format
• AD_FORMAT_BC2_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC2 compression) format with sRGB encoding
• AD_FORMAT_BC3_UNORM - 4 channel unsigned normalized block-compressed (BC3 compression) format
• AD_FORMAT_BC3_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC3 compression) format with sRGB encoding
• AD_FORMAT_BC4_UNORM - 1 channel unsigned normalized block-compressed (BC4 compression) format
• AD_FORMAT_BC4_SNORM - 1 channel signed normalized block-compressed (BC4 compression) format
• AD_FORMAT_BC5_UNORM - 2 channel unsigned normalized block-compressed (BC5 compression) format
• AD_FORMAT_BC5_SNORM - 2 channel signed normalized block-compressed (BC5 compression) format
• AD_FORMAT_BC6H_UF16 - 3 channel unsigned half-float block-compressed (BC6H compression) format
• AD_FORMAT_BC6H_SF16 - 3 channel signed half-float block-compressed (BC6H compression) format
• AD_FORMAT_BC7_UNORM - 4 channel unsigned normalized block-compressed (BC7 compression) format
• AD_FORMAT_BC7_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC7 compression) format with sRGB encoding

See Also:

• Constant Field Values

CU_AD_FORMAT_BC5_SNORM

public static final int CU_AD_FORMAT_BC5_SNORM

Array formats. (CUarray_format)

Enum values:

• AD_FORMAT_UNSIGNED_INT8 - Unsigned 8-bit integers
• AD_FORMAT_UNSIGNED_INT16 - Unsigned 16-bit integers
• AD_FORMAT_UNSIGNED_INT32 - Unsigned 32-bit integers
• AD_FORMAT_SIGNED_INT8 - Signed 8-bit integers
• AD_FORMAT_SIGNED_INT16 - Signed 16-bit integers
• AD_FORMAT_SIGNED_INT32 - Signed 32-bit integers
• AD_FORMAT_HALF - 16-bit floating point
• AD_FORMAT_FLOAT - 32-bit floating point
• AD_FORMAT_NV12 - 8-bit YUV planar format, with 4:2:0 sampling
• AD_FORMAT_UNORM_INT8X1 - 1 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT8X2 - 2 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT8X4 - 4 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT16X1 - 1 channel unsigned 16-bit normalized integer
• AD_FORMAT_UNORM_INT16X2 - 2 channel unsigned 16-bit normalized integer
• AD_FORMAT_UNORM_INT16X4 - 4 channel unsigned 16-bit normalized integer
• AD_FORMAT_SNORM_INT8X1 - 1 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT8X2 - 2 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT8X4 - 4 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT16X1 - 1 channel signed 16-bit normalized integer
• AD_FORMAT_SNORM_INT16X2 - 2 channel signed 16-bit normalized integer
• AD_FORMAT_SNORM_INT16X4 - 4 channel signed 16-bit normalized integer
• AD_FORMAT_BC1_UNORM - 4 channel unsigned normalized block-compressed (BC1 compression) format
• AD_FORMAT_BC1_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC1 compression) format with sRGB encoding
• AD_FORMAT_BC2_UNORM - 4 channel unsigned normalized block-compressed (BC2 compression) format
• AD_FORMAT_BC2_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC2 compression) format with sRGB encoding
• AD_FORMAT_BC3_UNORM - 4 channel unsigned normalized block-compressed (BC3 compression) format
• AD_FORMAT_BC3_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC3 compression) format with sRGB encoding
• AD_FORMAT_BC4_UNORM - 1 channel unsigned normalized block-compressed (BC4 compression) format
• AD_FORMAT_BC4_SNORM - 1 channel signed normalized block-compressed (BC4 compression) format
• AD_FORMAT_BC5_UNORM - 2 channel unsigned normalized block-compressed (BC5 compression) format
• AD_FORMAT_BC5_SNORM - 2 channel signed normalized block-compressed (BC5 compression) format
• AD_FORMAT_BC6H_UF16 - 3 channel unsigned half-float block-compressed (BC6H compression) format
• AD_FORMAT_BC6H_SF16 - 3 channel signed half-float block-compressed (BC6H compression) format
• AD_FORMAT_BC7_UNORM - 4 channel unsigned normalized block-compressed (BC7 compression) format
• AD_FORMAT_BC7_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC7 compression) format with sRGB encoding

See Also:

• Constant Field Values

CU_AD_FORMAT_BC6H_UF16

public static final int CU_AD_FORMAT_BC6H_UF16

Array formats. (CUarray_format)

Enum values:

• AD_FORMAT_UNSIGNED_INT8 - Unsigned 8-bit integers
• AD_FORMAT_UNSIGNED_INT16 - Unsigned 16-bit integers
• AD_FORMAT_UNSIGNED_INT32 - Unsigned 32-bit integers
• AD_FORMAT_SIGNED_INT8 - Signed 8-bit integers
• AD_FORMAT_SIGNED_INT16 - Signed 16-bit integers
• AD_FORMAT_SIGNED_INT32 - Signed 32-bit integers
• AD_FORMAT_HALF - 16-bit floating point
• AD_FORMAT_FLOAT - 32-bit floating point
• AD_FORMAT_NV12 - 8-bit YUV planar format, with 4:2:0 sampling
• AD_FORMAT_UNORM_INT8X1 - 1 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT8X2 - 2 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT8X4 - 4 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT16X1 - 1 channel unsigned 16-bit normalized integer
• AD_FORMAT_UNORM_INT16X2 - 2 channel unsigned 16-bit normalized integer
• AD_FORMAT_UNORM_INT16X4 - 4 channel unsigned 16-bit normalized integer
• AD_FORMAT_SNORM_INT8X1 - 1 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT8X2 - 2 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT8X4 - 4 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT16X1 - 1 channel signed 16-bit normalized integer
• AD_FORMAT_SNORM_INT16X2 - 2 channel signed 16-bit normalized integer
• AD_FORMAT_SNORM_INT16X4 - 4 channel signed 16-bit normalized integer
• AD_FORMAT_BC1_UNORM - 4 channel unsigned normalized block-compressed (BC1 compression) format
• AD_FORMAT_BC1_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC1 compression) format with sRGB encoding
• AD_FORMAT_BC2_UNORM - 4 channel unsigned normalized block-compressed (BC2 compression) format
• AD_FORMAT_BC2_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC2 compression) format with sRGB encoding
• AD_FORMAT_BC3_UNORM - 4 channel unsigned normalized block-compressed (BC3 compression) format
• AD_FORMAT_BC3_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC3 compression) format with sRGB encoding
• AD_FORMAT_BC4_UNORM - 1 channel unsigned normalized block-compressed (BC4 compression) format
• AD_FORMAT_BC4_SNORM - 1 channel signed normalized block-compressed (BC4 compression) format
• AD_FORMAT_BC5_UNORM - 2 channel unsigned normalized block-compressed (BC5 compression) format
• AD_FORMAT_BC5_SNORM - 2 channel signed normalized block-compressed (BC5 compression) format
• AD_FORMAT_BC6H_UF16 - 3 channel unsigned half-float block-compressed (BC6H compression) format
• AD_FORMAT_BC6H_SF16 - 3 channel signed half-float block-compressed (BC6H compression) format
• AD_FORMAT_BC7_UNORM - 4 channel unsigned normalized block-compressed (BC7 compression) format
• AD_FORMAT_BC7_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC7 compression) format with sRGB encoding

See Also:

• Constant Field Values

CU_AD_FORMAT_BC6H_SF16

public static final int CU_AD_FORMAT_BC6H_SF16

Array formats. (CUarray_format)

Enum values:

• AD_FORMAT_UNSIGNED_INT8 - Unsigned 8-bit integers
• AD_FORMAT_UNSIGNED_INT16 - Unsigned 16-bit integers
• AD_FORMAT_UNSIGNED_INT32 - Unsigned 32-bit integers
• AD_FORMAT_SIGNED_INT8 - Signed 8-bit integers
• AD_FORMAT_SIGNED_INT16 - Signed 16-bit integers
• AD_FORMAT_SIGNED_INT32 - Signed 32-bit integers
• AD_FORMAT_HALF - 16-bit floating point
• AD_FORMAT_FLOAT - 32-bit floating point
• AD_FORMAT_NV12 - 8-bit YUV planar format, with 4:2:0 sampling
• AD_FORMAT_UNORM_INT8X1 - 1 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT8X2 - 2 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT8X4 - 4 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT16X1 - 1 channel unsigned 16-bit normalized integer
• AD_FORMAT_UNORM_INT16X2 - 2 channel unsigned 16-bit normalized integer
• AD_FORMAT_UNORM_INT16X4 - 4 channel unsigned 16-bit normalized integer
• AD_FORMAT_SNORM_INT8X1 - 1 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT8X2 - 2 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT8X4 - 4 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT16X1 - 1 channel signed 16-bit normalized integer
• AD_FORMAT_SNORM_INT16X2 - 2 channel signed 16-bit normalized integer
• AD_FORMAT_SNORM_INT16X4 - 4 channel signed 16-bit normalized integer
• AD_FORMAT_BC1_UNORM - 4 channel unsigned normalized block-compressed (BC1 compression) format
• AD_FORMAT_BC1_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC1 compression) format with sRGB encoding
• AD_FORMAT_BC2_UNORM - 4 channel unsigned normalized block-compressed (BC2 compression) format
• AD_FORMAT_BC2_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC2 compression) format with sRGB encoding
• AD_FORMAT_BC3_UNORM - 4 channel unsigned normalized block-compressed (BC3 compression) format
• AD_FORMAT_BC3_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC3 compression) format with sRGB encoding
• AD_FORMAT_BC4_UNORM - 1 channel unsigned normalized block-compressed (BC4 compression) format
• AD_FORMAT_BC4_SNORM - 1 channel signed normalized block-compressed (BC4 compression) format
• AD_FORMAT_BC5_UNORM - 2 channel unsigned normalized block-compressed (BC5 compression) format
• AD_FORMAT_BC5_SNORM - 2 channel signed normalized block-compressed (BC5 compression) format
• AD_FORMAT_BC6H_UF16 - 3 channel unsigned half-float block-compressed (BC6H compression) format
• AD_FORMAT_BC6H_SF16 - 3 channel signed half-float block-compressed (BC6H compression) format
• AD_FORMAT_BC7_UNORM - 4 channel unsigned normalized block-compressed (BC7 compression) format
• AD_FORMAT_BC7_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC7 compression) format with sRGB encoding

See Also:

• Constant Field Values

CU_AD_FORMAT_BC7_UNORM

public static final int CU_AD_FORMAT_BC7_UNORM

Array formats. (CUarray_format)

Enum values:

• AD_FORMAT_UNSIGNED_INT8 - Unsigned 8-bit integers
• AD_FORMAT_UNSIGNED_INT16 - Unsigned 16-bit integers
• AD_FORMAT_UNSIGNED_INT32 - Unsigned 32-bit integers
• AD_FORMAT_SIGNED_INT8 - Signed 8-bit integers
• AD_FORMAT_SIGNED_INT16 - Signed 16-bit integers
• AD_FORMAT_SIGNED_INT32 - Signed 32-bit integers
• AD_FORMAT_HALF - 16-bit floating point
• AD_FORMAT_FLOAT - 32-bit floating point
• AD_FORMAT_NV12 - 8-bit YUV planar format, with 4:2:0 sampling
• AD_FORMAT_UNORM_INT8X1 - 1 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT8X2 - 2 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT8X4 - 4 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT16X1 - 1 channel unsigned 16-bit normalized integer
• AD_FORMAT_UNORM_INT16X2 - 2 channel unsigned 16-bit normalized integer
• AD_FORMAT_UNORM_INT16X4 - 4 channel unsigned 16-bit normalized integer
• AD_FORMAT_SNORM_INT8X1 - 1 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT8X2 - 2 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT8X4 - 4 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT16X1 - 1 channel signed 16-bit normalized integer
• AD_FORMAT_SNORM_INT16X2 - 2 channel signed 16-bit normalized integer
• AD_FORMAT_SNORM_INT16X4 - 4 channel signed 16-bit normalized integer
• AD_FORMAT_BC1_UNORM - 4 channel unsigned normalized block-compressed (BC1 compression) format
• AD_FORMAT_BC1_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC1 compression) format with sRGB encoding
• AD_FORMAT_BC2_UNORM - 4 channel unsigned normalized block-compressed (BC2 compression) format
• AD_FORMAT_BC2_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC2 compression) format with sRGB encoding
• AD_FORMAT_BC3_UNORM - 4 channel unsigned normalized block-compressed (BC3 compression) format
• AD_FORMAT_BC3_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC3 compression) format with sRGB encoding
• AD_FORMAT_BC4_UNORM - 1 channel unsigned normalized block-compressed (BC4 compression) format
• AD_FORMAT_BC4_SNORM - 1 channel signed normalized block-compressed (BC4 compression) format
• AD_FORMAT_BC5_UNORM - 2 channel unsigned normalized block-compressed (BC5 compression) format
• AD_FORMAT_BC5_SNORM - 2 channel signed normalized block-compressed (BC5 compression) format
• AD_FORMAT_BC6H_UF16 - 3 channel unsigned half-float block-compressed (BC6H compression) format
• AD_FORMAT_BC6H_SF16 - 3 channel signed half-float block-compressed (BC6H compression) format
• AD_FORMAT_BC7_UNORM - 4 channel unsigned normalized block-compressed (BC7 compression) format
• AD_FORMAT_BC7_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC7 compression) format with sRGB encoding

See Also:

• Constant Field Values

CU_AD_FORMAT_BC7_UNORM_SRGB

public static final int CU_AD_FORMAT_BC7_UNORM_SRGB

Array formats. (CUarray_format)

Enum values:

• AD_FORMAT_UNSIGNED_INT8 - Unsigned 8-bit integers
• AD_FORMAT_UNSIGNED_INT16 - Unsigned 16-bit integers
• AD_FORMAT_UNSIGNED_INT32 - Unsigned 32-bit integers
• AD_FORMAT_SIGNED_INT8 - Signed 8-bit integers
• AD_FORMAT_SIGNED_INT16 - Signed 16-bit integers
• AD_FORMAT_SIGNED_INT32 - Signed 32-bit integers
• AD_FORMAT_HALF - 16-bit floating point
• AD_FORMAT_FLOAT - 32-bit floating point
• AD_FORMAT_NV12 - 8-bit YUV planar format, with 4:2:0 sampling
• AD_FORMAT_UNORM_INT8X1 - 1 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT8X2 - 2 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT8X4 - 4 channel unsigned 8-bit normalized integer
• AD_FORMAT_UNORM_INT16X1 - 1 channel unsigned 16-bit normalized integer
• AD_FORMAT_UNORM_INT16X2 - 2 channel unsigned 16-bit normalized integer
• AD_FORMAT_UNORM_INT16X4 - 4 channel unsigned 16-bit normalized integer
• AD_FORMAT_SNORM_INT8X1 - 1 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT8X2 - 2 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT8X4 - 4 channel signed 8-bit normalized integer
• AD_FORMAT_SNORM_INT16X1 - 1 channel signed 16-bit normalized integer
• AD_FORMAT_SNORM_INT16X2 - 2 channel signed 16-bit normalized integer
• AD_FORMAT_SNORM_INT16X4 - 4 channel signed 16-bit normalized integer
• AD_FORMAT_BC1_UNORM - 4 channel unsigned normalized block-compressed (BC1 compression) format
• AD_FORMAT_BC1_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC1 compression) format with sRGB encoding
• AD_FORMAT_BC2_UNORM - 4 channel unsigned normalized block-compressed (BC2 compression) format
• AD_FORMAT_BC2_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC2 compression) format with sRGB encoding
• AD_FORMAT_BC3_UNORM - 4 channel unsigned normalized block-compressed (BC3 compression) format
• AD_FORMAT_BC3_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC3 compression) format with sRGB encoding
• AD_FORMAT_BC4_UNORM - 1 channel unsigned normalized block-compressed (BC4 compression) format
• AD_FORMAT_BC4_SNORM - 1 channel signed normalized block-compressed (BC4 compression) format
• AD_FORMAT_BC5_UNORM - 2 channel unsigned normalized block-compressed (BC5 compression) format
• AD_FORMAT_BC5_SNORM - 2 channel signed normalized block-compressed (BC5 compression) format
• AD_FORMAT_BC6H_UF16 - 3 channel unsigned half-float block-compressed (BC6H compression) format
• AD_FORMAT_BC6H_SF16 - 3 channel signed half-float block-compressed (BC6H compression) format
• AD_FORMAT_BC7_UNORM - 4 channel unsigned normalized block-compressed (BC7 compression) format
• AD_FORMAT_BC7_UNORM_SRGB - 4 channel unsigned normalized block-compressed (BC7 compression) format with sRGB encoding

See Also:

• Constant Field Values

CU_TR_ADDRESS_MODE_WRAP

public static final int CU_TR_ADDRESS_MODE_WRAP

Texture reference addressing modes. (CUaddress_mode)

Enum values:

• TR_ADDRESS_MODE_WRAP - Wrapping address mode
• TR_ADDRESS_MODE_CLAMP - Clamp to edge address mode
• TR_ADDRESS_MODE_MIRROR - Mirror address mode
• TR_ADDRESS_MODE_BORDER - Border address mode

See Also:

• Constant Field Values

CU_TR_ADDRESS_MODE_CLAMP

public static final int CU_TR_ADDRESS_MODE_CLAMP

Texture reference addressing modes. (CUaddress_mode)

Enum values:

• TR_ADDRESS_MODE_WRAP - Wrapping address mode
• TR_ADDRESS_MODE_CLAMP - Clamp to edge address mode
• TR_ADDRESS_MODE_MIRROR - Mirror address mode
• TR_ADDRESS_MODE_BORDER - Border address mode

See Also:

• Constant Field Values

CU_TR_ADDRESS_MODE_MIRROR

public static final int CU_TR_ADDRESS_MODE_MIRROR

Texture reference addressing modes. (CUaddress_mode)

Enum values:

• TR_ADDRESS_MODE_WRAP - Wrapping address mode
• TR_ADDRESS_MODE_CLAMP - Clamp to edge address mode
• TR_ADDRESS_MODE_MIRROR - Mirror address mode
• TR_ADDRESS_MODE_BORDER - Border address mode

See Also:

• Constant Field Values

CU_TR_ADDRESS_MODE_BORDER

public static final int CU_TR_ADDRESS_MODE_BORDER

Texture reference addressing modes. (CUaddress_mode)

Enum values:

• TR_ADDRESS_MODE_WRAP - Wrapping address mode
• TR_ADDRESS_MODE_CLAMP - Clamp to edge address mode
• TR_ADDRESS_MODE_MIRROR - Mirror address mode
• TR_ADDRESS_MODE_BORDER - Border address mode

See Also:

• Constant Field Values

CU_TR_FILTER_MODE_POINT

public static final int CU_TR_FILTER_MODE_POINT

Texture reference filtering modes. (CUfilter_mode)

Enum values:

• TR_FILTER_MODE_POINT - Point filter mode
• TR_FILTER_MODE_LINEAR - Linear filter mode

See Also:

• Constant Field Values

CU_TR_FILTER_MODE_LINEAR

public static final int CU_TR_FILTER_MODE_LINEAR

Texture reference filtering modes. (CUfilter_mode)

Enum values:

• TR_FILTER_MODE_POINT - Point filter mode
• TR_FILTER_MODE_LINEAR - Linear filter mode

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK

public static final int CU_DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X

public static final int CU_DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y

public static final int CU_DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z

public static final int CU_DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_MAX_GRID_DIM_X

public static final int CU_DEVICE_ATTRIBUTE_MAX_GRID_DIM_X

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y

public static final int CU_DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z

public static final int CU_DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK

public static final int CU_DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK

public static final int CU_DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY

public static final int CU_DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_WARP_SIZE

public static final int CU_DEVICE_ATTRIBUTE_WARP_SIZE

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_MAX_PITCH

public static final int CU_DEVICE_ATTRIBUTE_MAX_PITCH

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK

public static final int CU_DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK

public static final int CU_DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_CLOCK_RATE

public static final int CU_DEVICE_ATTRIBUTE_CLOCK_RATE

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT

public static final int CU_DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_GPU_OVERLAP

public static final int CU_DEVICE_ATTRIBUTE_GPU_OVERLAP

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT

public static final int CU_DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT

public static final int CU_DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_INTEGRATED

public static final int CU_DEVICE_ATTRIBUTE_INTEGRATED

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY

public static final int CU_DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_COMPUTE_MODE

public static final int CU_DEVICE_ATTRIBUTE_COMPUTE_MODE

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH

public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH

public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT

public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH

public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT

public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH

public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH

public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT

public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS

public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH

public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT

public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES

public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT

public static final int CU_DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_CONCURRENT_KERNELS

public static final int CU_DEVICE_ATTRIBUTE_CONCURRENT_KERNELS

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_ECC_ENABLED

public static final int CU_DEVICE_ATTRIBUTE_ECC_ENABLED

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_PCI_BUS_ID

public static final int CU_DEVICE_ATTRIBUTE_PCI_BUS_ID

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_PCI_DEVICE_ID

public static final int CU_DEVICE_ATTRIBUTE_PCI_DEVICE_ID

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_TCC_DRIVER

public static final int CU_DEVICE_ATTRIBUTE_TCC_DRIVER

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE

public static final int CU_DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH

public static final int CU_DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_L2_CACHE_SIZE

public static final int CU_DEVICE_ATTRIBUTE_L2_CACHE_SIZE

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR

public static final int CU_DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT

public static final int CU_DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING

public static final int CU_DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH

public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS

public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER

public static final int CU_DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH

public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT

public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE

public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE

public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE

public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_PCI_DOMAIN_ID

public static final int CU_DEVICE_ATTRIBUTE_PCI_DOMAIN_ID

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT

public static final int CU_DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH

public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH

public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS

public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH

public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH

public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT

public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH

public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT

public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH

public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH

public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS

public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH

public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT

public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS

public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH

public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH

public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS

public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH

public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH

public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT

public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH

public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH

public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT

public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR

public static final int CU_DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR

public static final int CU_DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH

public static final int CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED

public static final int CU_DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED

public static final int CU_DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED

public static final int CU_DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR

public static final int CU_DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR

public static final int CU_DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_MANAGED_MEMORY

public static final int CU_DEVICE_ATTRIBUTE_MANAGED_MEMORY

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_MULTI_GPU_BOARD

public static final int CU_DEVICE_ATTRIBUTE_MULTI_GPU_BOARD

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID

public static final int CU_DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED

public static final int CU_DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO

public static final int CU_DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS

public static final int CU_DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS

public static final int CU_DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED

public static final int CU_DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM

public static final int CU_DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS

public static final int CU_DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS

public static final int CU_DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR

public static final int CU_DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH

public static final int CU_DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH

public static final int CU_DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN

public static final int CU_DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES

public static final int CU_DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED

public static final int CU_DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES

public static final int CU_DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST

public static final int CU_DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED

public static final int CU_DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED

public static final int CU_DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED

public static final int CU_DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED

public static final int CU_DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED

public static final int CU_DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR

public static final int CU_DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED

public static final int CU_DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE

public static final int CU_DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE

public static final int CU_DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED

public static final int CU_DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK

public static final int CU_DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED

public static final int CU_DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED

public static final int CU_DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED

public static final int CU_DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED

public static final int CU_DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED

public static final int CU_DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS

public static final int CU_DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING

public static final int CU_DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES

public static final int CU_DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES

Device properties. (CUdevice_attribute)

Enum values:

• DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK - Maximum number of threads per block
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X - Maximum block dimension X
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y - Maximum block dimension Y
• DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z - Maximum block dimension Z
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_X - Maximum grid dimension X
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y - Maximum grid dimension Y
• DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z - Maximum grid dimension Z
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK - Maximum shared memory available per block in bytes
• DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK
• DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY - Memory available on device for __constant__ variables in a CUDA C kernel in bytes
• DEVICE_ATTRIBUTE_WARP_SIZE - Warp size in threads
• DEVICE_ATTRIBUTE_MAX_PITCH - Maximum pitch in bytes allowed by memory copies
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK - Maximum number of 32-bit registers available per block
• DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK - Deprecated, use DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK
• DEVICE_ATTRIBUTE_CLOCK_RATE - Typical clock frequency in kilohertz
• DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT - Alignment requirement for textures
• DEVICE_ATTRIBUTE_GPU_OVERLAP - Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT.
• DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT - Number of multiprocessors on device
• DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT - Specifies whether there is a run time limit on kernels
• DEVICE_ATTRIBUTE_INTEGRATED - Device is integrated with host memory
• DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY - Device can map host memory into CUDA address space
• DEVICE_ATTRIBUTE_COMPUTE_MODE - Compute mode (See CUcomputemode for details)
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH - Maximum 1D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH - Maximum 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT - Maximum 2D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH - Maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT - Maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH - Maximum 3D texture depth
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH - Maximum 2D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT - Maximum 2D layered texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS - Maximum layers in a 2D layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES - Deprecated, use DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS
• DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT - Alignment requirement for surfaces
• DEVICE_ATTRIBUTE_CONCURRENT_KERNELS - Device can possibly execute multiple kernels concurrently
• DEVICE_ATTRIBUTE_ECC_ENABLED - Device has ECC support enabled
• DEVICE_ATTRIBUTE_PCI_BUS_ID - PCI bus ID of the device
• DEVICE_ATTRIBUTE_PCI_DEVICE_ID - PCI device ID of the device
• DEVICE_ATTRIBUTE_TCC_DRIVER - Device is using TCC driver model
• DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE - Peak memory clock frequency in kilohertz
• DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH - Global memory bus width in bits
• DEVICE_ATTRIBUTE_L2_CACHE_SIZE - Size of L2 cache in bytes
• DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR - Maximum resident threads per multiprocessor
• DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT - Number of asynchronous engines
• DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING - Device shares a unified address space with the host
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH - Maximum 1D layered texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS - Maximum layers in a 1D layered texture
• DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER - Deprecated, do not use.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH - Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT - Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE - Alternate maximum 3D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE - Alternate maximum 3D texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE - Alternate maximum 3D texture depth
• DEVICE_ATTRIBUTE_PCI_DOMAIN_ID - PCI domain ID of the device
• DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT - Pitch alignment requirement for textures
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH - Maximum cubemap texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered texture width/height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered texture
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH - Maximum 1D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH - Maximum 2D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT - Maximum 2D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH - Maximum 3D surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT - Maximum 3D surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH - Maximum 3D surface depth
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH - Maximum 1D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS - Maximum layers in a 1D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH - Maximum 2D layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT - Maximum 2D layered surface height
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS - Maximum layers in a 2D layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH - Maximum cubemap surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH - Maximum cubemap layered surface width
• DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS - Maximum layers in a cubemap layered surface
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH - Deprecated, do not use. Use cudaDeviceGetTexture1DLinearMaxWidth() or DeviceGetTexture1DLinearMaxWidth instead.
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH - Maximum 2D linear texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT - Maximum 2D linear texture height
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH - Maximum 2D linear texture pitch in bytes
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH - Maximum mipmapped 2D texture width
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT - Maximum mipmapped 2D texture height
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR - Major compute capability version number
• DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR - Minor compute capability version number
• DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH - Maximum mipmapped 1D texture width
• DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED - Device supports stream priorities
• DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED - Device supports caching globals in L1
• DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED - Device supports caching locals in L1
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR - Maximum shared memory available per multiprocessor in bytes
• DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR - Maximum number of 32-bit registers available per multiprocessor
• DEVICE_ATTRIBUTE_MANAGED_MEMORY - Device can allocate managed memory on this system
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD - Device is on a multi-GPU board
• DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID - Unique id for a group of devices on the same multi-GPU board
• DEVICE_ATTRIBUTE_HOST_NATIVE_ATOMIC_SUPPORTED - Link between the device and the host supports native atomic operations (this is a placeholder attribute, and is not supported on any current hardware)
• DEVICE_ATTRIBUTE_SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO - Ratio of single precision performance (in floating-point operations per second) to double precision performance
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS - Device supports coherently accessing pageable memory without calling cudaHostRegister on it
• DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS - Device can coherently access managed memory concurrently with the CPU
• DEVICE_ATTRIBUTE_COMPUTE_PREEMPTION_SUPPORTED - Device supports compute preemption.
• DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM - Device can access host registered memory at the same virtual address as the CPU
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS - StreamBatchMemOp and related APIs are supported.
• DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS - 64-bit operations are supported in StreamBatchMemOp and related APIs.
• DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR - STREAM_WAIT_VALUE_NOR is supported.
• DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH - Device supports launching cooperative kernels via LaunchCooperativeKernel
• DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH - Deprecated, LaunchCooperativeKernelMultiDevice is deprecated.
• DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN - Maximum optin shared memory per block
• DEVICE_ATTRIBUTE_CAN_FLUSH_REMOTE_WRITES - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device. See CUDA_MEMOP for additional details.
• DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED - Device supports host memory registration via cudaHostRegister().
• DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES - Device accesses pageable memory via the host's page tables.
• DEVICE_ATTRIBUTE_DIRECT_MANAGED_MEM_ACCESS_FROM_HOST - The host can directly access managed memory on the device without migration.
• DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED - Deprecated, Use DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED
• DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED - Device supports virtual memory management APIs like MemAddressReserve, MemCreate, MemMap and related APIs
• DEVICE_ATTRIBUTE_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR_SUPPORTED - Device supports exporting memory to a posix file descriptor with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 NT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_HANDLE_TYPE_WIN32_KMT_HANDLE_SUPPORTED - Device supports exporting memory to a Win32 KMT handle with MemExportToShareableHandle, if requested via MemCreate
• DEVICE_ATTRIBUTE_MAX_BLOCKS_PER_MULTIPROCESSOR - Maximum number of blocks per multiprocessor
• DEVICE_ATTRIBUTE_GENERIC_COMPRESSION_SUPPORTED - Device supports compression of memory
• DEVICE_ATTRIBUTE_MAX_PERSISTING_L2_CACHE_SIZE - Maximum L2 persisting lines capacity setting in bytes.
• DEVICE_ATTRIBUTE_MAX_ACCESS_POLICY_WINDOW_SIZE - Maximum value of CUaccessPolicyWindow{@code num_bytes}.
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WITH_CUDA_VMM_SUPPORTED - Device supports specifying the GPUDirect RDMA flag with MemCreate
• DEVICE_ATTRIBUTE_RESERVED_SHARED_MEMORY_PER_BLOCK - Shared memory reserved by CUDA driver per block in bytes
• DEVICE_ATTRIBUTE_SPARSE_CUDA_ARRAY_SUPPORTED - Device supports sparse CUDA arrays and sparse CUDA mipmapped arrays
• DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED - Device supports using the MemHostRegister flag MEMHOSTREGISTER_READ_ONLY to register memory that must be mapped as read-only to the GPU
• DEVICE_ATTRIBUTE_TIMELINE_SEMAPHORE_INTEROP_SUPPORTED - External timeline semaphore interop is supported on the device
• DEVICE_ATTRIBUTE_MEMORY_POOLS_SUPPORTED - Device supports using the MemAllocAsync and cuMemPool* family of APIs
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED - Device supports GPUDirect RDMA APIs, like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information)
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS - The returned attribute shall be interpreted as a bitmask, where the individual bits are described by the CUflushGPUDirectRDMAWritesOptions enum
• DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING - GPUDirect RDMA writes to the device do not need to be flushed for consumers within the scope indicated by the returned attribute. See CUGPUDirectRDMAWritesOrdering for the numerical values returned here.
• DEVICE_ATTRIBUTE_MEMPOOL_SUPPORTED_HANDLE_TYPES - Handle types supported with mempool based IPC

See Also:

• Constant Field Values

CU_POINTER_ATTRIBUTE_CONTEXT

public static final int CU_POINTER_ATTRIBUTE_CONTEXT

Pointer information. (CUpointer_attribute)

Enum values:

• POINTER_ATTRIBUTE_CONTEXT - The CUcontext on which a pointer was allocated or registered
• POINTER_ATTRIBUTE_MEMORY_TYPE - The CUmemorytype describing the physical location of a pointer
• POINTER_ATTRIBUTE_DEVICE_POINTER - The address at which a pointer's memory may be accessed on the device
• POINTER_ATTRIBUTE_HOST_POINTER - The address at which a pointer's memory may be accessed on the host
• POINTER_ATTRIBUTE_P2P_TOKENS - A pair of tokens for use with the nv-p2p.h Linux kernel interface
• POINTER_ATTRIBUTE_SYNC_MEMOPS - Synchronize every synchronous memory operation initiated on this region
• POINTER_ATTRIBUTE_BUFFER_ID - A process-wide unique ID for an allocated memory region
• POINTER_ATTRIBUTE_IS_MANAGED - Indicates if the pointer points to managed memory
• POINTER_ATTRIBUTE_DEVICE_ORDINAL - A device ordinal of a device on which a pointer was allocated or registered
• POINTER_ATTRIBUTE_IS_LEGACY_CUDA_IPC_CAPABLE - 1 if this pointer maps to an allocation that is suitable for cudaIpcGetMemHandle(), 0 otherwise
• POINTER_ATTRIBUTE_RANGE_START_ADDR - Starting address for this requested pointer
• POINTER_ATTRIBUTE_RANGE_SIZE - Size of the address range for this requested pointer
• POINTER_ATTRIBUTE_MAPPED - 1 if this pointer is in a valid address range that is mapped to a backing allocation, 0 otherwise
• POINTER_ATTRIBUTE_ALLOWED_HANDLE_TYPES - Bitmask of allowed CUmemAllocationHandleType for this allocation
• POINTER_ATTRIBUTE_IS_GPU_DIRECT_RDMA_CAPABLE - 1 if the memory this pointer is referencing can be used with the GPUDirect RDMA API
• POINTER_ATTRIBUTE_ACCESS_FLAGS - Returns the access flags the device associated with the current context has on the corresponding memory referenced by the pointer given
• POINTER_ATTRIBUTE_MEMPOOL_HANDLE - Returns the mempool handle for the allocation if it was allocated from a mempool. Otherwise returns NULL.

See Also:

• Constant Field Values

CU_POINTER_ATTRIBUTE_MEMORY_TYPE

public static final int CU_POINTER_ATTRIBUTE_MEMORY_TYPE

Pointer information. (CUpointer_attribute)

Enum values:

• POINTER_ATTRIBUTE_CONTEXT - The CUcontext on which a pointer was allocated or registered
• POINTER_ATTRIBUTE_MEMORY_TYPE - The CUmemorytype describing the physical location of a pointer
• POINTER_ATTRIBUTE_DEVICE_POINTER - The address at which a pointer's memory may be accessed on the device
• POINTER_ATTRIBUTE_HOST_POINTER - The address at which a pointer's memory may be accessed on the host
• POINTER_ATTRIBUTE_P2P_TOKENS - A pair of tokens for use with the nv-p2p.h Linux kernel interface
• POINTER_ATTRIBUTE_SYNC_MEMOPS - Synchronize every synchronous memory operation initiated on this region
• POINTER_ATTRIBUTE_BUFFER_ID - A process-wide unique ID for an allocated memory region
• POINTER_ATTRIBUTE_IS_MANAGED - Indicates if the pointer points to managed memory
• POINTER_ATTRIBUTE_DEVICE_ORDINAL - A device ordinal of a device on which a pointer was allocated or registered
• POINTER_ATTRIBUTE_IS_LEGACY_CUDA_IPC_CAPABLE - 1 if this pointer maps to an allocation that is suitable for cudaIpcGetMemHandle(), 0 otherwise
• POINTER_ATTRIBUTE_RANGE_START_ADDR - Starting address for this requested pointer
• POINTER_ATTRIBUTE_RANGE_SIZE - Size of the address range for this requested pointer
• POINTER_ATTRIBUTE_MAPPED - 1 if this pointer is in a valid address range that is mapped to a backing allocation, 0 otherwise
• POINTER_ATTRIBUTE_ALLOWED_HANDLE_TYPES - Bitmask of allowed CUmemAllocationHandleType for this allocation
• POINTER_ATTRIBUTE_IS_GPU_DIRECT_RDMA_CAPABLE - 1 if the memory this pointer is referencing can be used with the GPUDirect RDMA API
• POINTER_ATTRIBUTE_ACCESS_FLAGS - Returns the access flags the device associated with the current context has on the corresponding memory referenced by the pointer given
• POINTER_ATTRIBUTE_MEMPOOL_HANDLE - Returns the mempool handle for the allocation if it was allocated from a mempool. Otherwise returns NULL.

See Also:

• Constant Field Values

CU_POINTER_ATTRIBUTE_DEVICE_POINTER

public static final int CU_POINTER_ATTRIBUTE_DEVICE_POINTER

Pointer information. (CUpointer_attribute)

Enum values:

• POINTER_ATTRIBUTE_CONTEXT - The CUcontext on which a pointer was allocated or registered
• POINTER_ATTRIBUTE_MEMORY_TYPE - The CUmemorytype describing the physical location of a pointer
• POINTER_ATTRIBUTE_DEVICE_POINTER - The address at which a pointer's memory may be accessed on the device
• POINTER_ATTRIBUTE_HOST_POINTER - The address at which a pointer's memory may be accessed on the host
• POINTER_ATTRIBUTE_P2P_TOKENS - A pair of tokens for use with the nv-p2p.h Linux kernel interface
• POINTER_ATTRIBUTE_SYNC_MEMOPS - Synchronize every synchronous memory operation initiated on this region
• POINTER_ATTRIBUTE_BUFFER_ID - A process-wide unique ID for an allocated memory region
• POINTER_ATTRIBUTE_IS_MANAGED - Indicates if the pointer points to managed memory
• POINTER_ATTRIBUTE_DEVICE_ORDINAL - A device ordinal of a device on which a pointer was allocated or registered
• POINTER_ATTRIBUTE_IS_LEGACY_CUDA_IPC_CAPABLE - 1 if this pointer maps to an allocation that is suitable for cudaIpcGetMemHandle(), 0 otherwise
• POINTER_ATTRIBUTE_RANGE_START_ADDR - Starting address for this requested pointer
• POINTER_ATTRIBUTE_RANGE_SIZE - Size of the address range for this requested pointer
• POINTER_ATTRIBUTE_MAPPED - 1 if this pointer is in a valid address range that is mapped to a backing allocation, 0 otherwise
• POINTER_ATTRIBUTE_ALLOWED_HANDLE_TYPES - Bitmask of allowed CUmemAllocationHandleType for this allocation
• POINTER_ATTRIBUTE_IS_GPU_DIRECT_RDMA_CAPABLE - 1 if the memory this pointer is referencing can be used with the GPUDirect RDMA API
• POINTER_ATTRIBUTE_ACCESS_FLAGS - Returns the access flags the device associated with the current context has on the corresponding memory referenced by the pointer given
• POINTER_ATTRIBUTE_MEMPOOL_HANDLE - Returns the mempool handle for the allocation if it was allocated from a mempool. Otherwise returns NULL.

See Also:

• Constant Field Values

CU_POINTER_ATTRIBUTE_HOST_POINTER

public static final int CU_POINTER_ATTRIBUTE_HOST_POINTER

Pointer information. (CUpointer_attribute)

Enum values:

• POINTER_ATTRIBUTE_CONTEXT - The CUcontext on which a pointer was allocated or registered
• POINTER_ATTRIBUTE_MEMORY_TYPE - The CUmemorytype describing the physical location of a pointer
• POINTER_ATTRIBUTE_DEVICE_POINTER - The address at which a pointer's memory may be accessed on the device
• POINTER_ATTRIBUTE_HOST_POINTER - The address at which a pointer's memory may be accessed on the host
• POINTER_ATTRIBUTE_P2P_TOKENS - A pair of tokens for use with the nv-p2p.h Linux kernel interface
• POINTER_ATTRIBUTE_SYNC_MEMOPS - Synchronize every synchronous memory operation initiated on this region
• POINTER_ATTRIBUTE_BUFFER_ID - A process-wide unique ID for an allocated memory region
• POINTER_ATTRIBUTE_IS_MANAGED - Indicates if the pointer points to managed memory
• POINTER_ATTRIBUTE_DEVICE_ORDINAL - A device ordinal of a device on which a pointer was allocated or registered
• POINTER_ATTRIBUTE_IS_LEGACY_CUDA_IPC_CAPABLE - 1 if this pointer maps to an allocation that is suitable for cudaIpcGetMemHandle(), 0 otherwise
• POINTER_ATTRIBUTE_RANGE_START_ADDR - Starting address for this requested pointer
• POINTER_ATTRIBUTE_RANGE_SIZE - Size of the address range for this requested pointer
• POINTER_ATTRIBUTE_MAPPED - 1 if this pointer is in a valid address range that is mapped to a backing allocation, 0 otherwise
• POINTER_ATTRIBUTE_ALLOWED_HANDLE_TYPES - Bitmask of allowed CUmemAllocationHandleType for this allocation
• POINTER_ATTRIBUTE_IS_GPU_DIRECT_RDMA_CAPABLE - 1 if the memory this pointer is referencing can be used with the GPUDirect RDMA API
• POINTER_ATTRIBUTE_ACCESS_FLAGS - Returns the access flags the device associated with the current context has on the corresponding memory referenced by the pointer given
• POINTER_ATTRIBUTE_MEMPOOL_HANDLE - Returns the mempool handle for the allocation if it was allocated from a mempool. Otherwise returns NULL.

See Also:

• Constant Field Values

CU_POINTER_ATTRIBUTE_P2P_TOKENS

public static final int CU_POINTER_ATTRIBUTE_P2P_TOKENS

Pointer information. (CUpointer_attribute)

Enum values:

• POINTER_ATTRIBUTE_CONTEXT - The CUcontext on which a pointer was allocated or registered
• POINTER_ATTRIBUTE_MEMORY_TYPE - The CUmemorytype describing the physical location of a pointer
• POINTER_ATTRIBUTE_DEVICE_POINTER - The address at which a pointer's memory may be accessed on the device
• POINTER_ATTRIBUTE_HOST_POINTER - The address at which a pointer's memory may be accessed on the host
• POINTER_ATTRIBUTE_P2P_TOKENS - A pair of tokens for use with the nv-p2p.h Linux kernel interface
• POINTER_ATTRIBUTE_SYNC_MEMOPS - Synchronize every synchronous memory operation initiated on this region
• POINTER_ATTRIBUTE_BUFFER_ID - A process-wide unique ID for an allocated memory region
• POINTER_ATTRIBUTE_IS_MANAGED - Indicates if the pointer points to managed memory
• POINTER_ATTRIBUTE_DEVICE_ORDINAL - A device ordinal of a device on which a pointer was allocated or registered
• POINTER_ATTRIBUTE_IS_LEGACY_CUDA_IPC_CAPABLE - 1 if this pointer maps to an allocation that is suitable for cudaIpcGetMemHandle(), 0 otherwise
• POINTER_ATTRIBUTE_RANGE_START_ADDR - Starting address for this requested pointer
• POINTER_ATTRIBUTE_RANGE_SIZE - Size of the address range for this requested pointer
• POINTER_ATTRIBUTE_MAPPED - 1 if this pointer is in a valid address range that is mapped to a backing allocation, 0 otherwise
• POINTER_ATTRIBUTE_ALLOWED_HANDLE_TYPES - Bitmask of allowed CUmemAllocationHandleType for this allocation
• POINTER_ATTRIBUTE_IS_GPU_DIRECT_RDMA_CAPABLE - 1 if the memory this pointer is referencing can be used with the GPUDirect RDMA API
• POINTER_ATTRIBUTE_ACCESS_FLAGS - Returns the access flags the device associated with the current context has on the corresponding memory referenced by the pointer given
• POINTER_ATTRIBUTE_MEMPOOL_HANDLE - Returns the mempool handle for the allocation if it was allocated from a mempool. Otherwise returns NULL.

See Also:

• Constant Field Values

CU_POINTER_ATTRIBUTE_SYNC_MEMOPS

public static final int CU_POINTER_ATTRIBUTE_SYNC_MEMOPS

Pointer information. (CUpointer_attribute)

Enum values:

• POINTER_ATTRIBUTE_CONTEXT - The CUcontext on which a pointer was allocated or registered
• POINTER_ATTRIBUTE_MEMORY_TYPE - The CUmemorytype describing the physical location of a pointer
• POINTER_ATTRIBUTE_DEVICE_POINTER - The address at which a pointer's memory may be accessed on the device
• POINTER_ATTRIBUTE_HOST_POINTER - The address at which a pointer's memory may be accessed on the host
• POINTER_ATTRIBUTE_P2P_TOKENS - A pair of tokens for use with the nv-p2p.h Linux kernel interface
• POINTER_ATTRIBUTE_SYNC_MEMOPS - Synchronize every synchronous memory operation initiated on this region
• POINTER_ATTRIBUTE_BUFFER_ID - A process-wide unique ID for an allocated memory region
• POINTER_ATTRIBUTE_IS_MANAGED - Indicates if the pointer points to managed memory
• POINTER_ATTRIBUTE_DEVICE_ORDINAL - A device ordinal of a device on which a pointer was allocated or registered
• POINTER_ATTRIBUTE_IS_LEGACY_CUDA_IPC_CAPABLE - 1 if this pointer maps to an allocation that is suitable for cudaIpcGetMemHandle(), 0 otherwise
• POINTER_ATTRIBUTE_RANGE_START_ADDR - Starting address for this requested pointer
• POINTER_ATTRIBUTE_RANGE_SIZE - Size of the address range for this requested pointer
• POINTER_ATTRIBUTE_MAPPED - 1 if this pointer is in a valid address range that is mapped to a backing allocation, 0 otherwise
• POINTER_ATTRIBUTE_ALLOWED_HANDLE_TYPES - Bitmask of allowed CUmemAllocationHandleType for this allocation
• POINTER_ATTRIBUTE_IS_GPU_DIRECT_RDMA_CAPABLE - 1 if the memory this pointer is referencing can be used with the GPUDirect RDMA API
• POINTER_ATTRIBUTE_ACCESS_FLAGS - Returns the access flags the device associated with the current context has on the corresponding memory referenced by the pointer given
• POINTER_ATTRIBUTE_MEMPOOL_HANDLE - Returns the mempool handle for the allocation if it was allocated from a mempool. Otherwise returns NULL.

See Also:

• Constant Field Values

CU_POINTER_ATTRIBUTE_BUFFER_ID

public static final int CU_POINTER_ATTRIBUTE_BUFFER_ID

Pointer information. (CUpointer_attribute)

Enum values:

• POINTER_ATTRIBUTE_CONTEXT - The CUcontext on which a pointer was allocated or registered
• POINTER_ATTRIBUTE_MEMORY_TYPE - The CUmemorytype describing the physical location of a pointer
• POINTER_ATTRIBUTE_DEVICE_POINTER - The address at which a pointer's memory may be accessed on the device
• POINTER_ATTRIBUTE_HOST_POINTER - The address at which a pointer's memory may be accessed on the host
• POINTER_ATTRIBUTE_P2P_TOKENS - A pair of tokens for use with the nv-p2p.h Linux kernel interface
• POINTER_ATTRIBUTE_SYNC_MEMOPS - Synchronize every synchronous memory operation initiated on this region
• POINTER_ATTRIBUTE_BUFFER_ID - A process-wide unique ID for an allocated memory region
• POINTER_ATTRIBUTE_IS_MANAGED - Indicates if the pointer points to managed memory
• POINTER_ATTRIBUTE_DEVICE_ORDINAL - A device ordinal of a device on which a pointer was allocated or registered
• POINTER_ATTRIBUTE_IS_LEGACY_CUDA_IPC_CAPABLE - 1 if this pointer maps to an allocation that is suitable for cudaIpcGetMemHandle(), 0 otherwise
• POINTER_ATTRIBUTE_RANGE_START_ADDR - Starting address for this requested pointer
• POINTER_ATTRIBUTE_RANGE_SIZE - Size of the address range for this requested pointer
• POINTER_ATTRIBUTE_MAPPED - 1 if this pointer is in a valid address range that is mapped to a backing allocation, 0 otherwise
• POINTER_ATTRIBUTE_ALLOWED_HANDLE_TYPES - Bitmask of allowed CUmemAllocationHandleType for this allocation
• POINTER_ATTRIBUTE_IS_GPU_DIRECT_RDMA_CAPABLE - 1 if the memory this pointer is referencing can be used with the GPUDirect RDMA API
• POINTER_ATTRIBUTE_ACCESS_FLAGS - Returns the access flags the device associated with the current context has on the corresponding memory referenced by the pointer given
• POINTER_ATTRIBUTE_MEMPOOL_HANDLE - Returns the mempool handle for the allocation if it was allocated from a mempool. Otherwise returns NULL.

See Also:

• Constant Field Values

CU_POINTER_ATTRIBUTE_IS_MANAGED

public static final int CU_POINTER_ATTRIBUTE_IS_MANAGED

Pointer information. (CUpointer_attribute)

Enum values:

• POINTER_ATTRIBUTE_CONTEXT - The CUcontext on which a pointer was allocated or registered
• POINTER_ATTRIBUTE_MEMORY_TYPE - The CUmemorytype describing the physical location of a pointer
• POINTER_ATTRIBUTE_DEVICE_POINTER - The address at which a pointer's memory may be accessed on the device
• POINTER_ATTRIBUTE_HOST_POINTER - The address at which a pointer's memory may be accessed on the host
• POINTER_ATTRIBUTE_P2P_TOKENS - A pair of tokens for use with the nv-p2p.h Linux kernel interface
• POINTER_ATTRIBUTE_SYNC_MEMOPS - Synchronize every synchronous memory operation initiated on this region
• POINTER_ATTRIBUTE_BUFFER_ID - A process-wide unique ID for an allocated memory region
• POINTER_ATTRIBUTE_IS_MANAGED - Indicates if the pointer points to managed memory
• POINTER_ATTRIBUTE_DEVICE_ORDINAL - A device ordinal of a device on which a pointer was allocated or registered
• POINTER_ATTRIBUTE_IS_LEGACY_CUDA_IPC_CAPABLE - 1 if this pointer maps to an allocation that is suitable for cudaIpcGetMemHandle(), 0 otherwise
• POINTER_ATTRIBUTE_RANGE_START_ADDR - Starting address for this requested pointer
• POINTER_ATTRIBUTE_RANGE_SIZE - Size of the address range for this requested pointer
• POINTER_ATTRIBUTE_MAPPED - 1 if this pointer is in a valid address range that is mapped to a backing allocation, 0 otherwise
• POINTER_ATTRIBUTE_ALLOWED_HANDLE_TYPES - Bitmask of allowed CUmemAllocationHandleType for this allocation
• POINTER_ATTRIBUTE_IS_GPU_DIRECT_RDMA_CAPABLE - 1 if the memory this pointer is referencing can be used with the GPUDirect RDMA API
• POINTER_ATTRIBUTE_ACCESS_FLAGS - Returns the access flags the device associated with the current context has on the corresponding memory referenced by the pointer given
• POINTER_ATTRIBUTE_MEMPOOL_HANDLE - Returns the mempool handle for the allocation if it was allocated from a mempool. Otherwise returns NULL.

See Also:

• Constant Field Values

CU_POINTER_ATTRIBUTE_DEVICE_ORDINAL

public static final int CU_POINTER_ATTRIBUTE_DEVICE_ORDINAL

Pointer information. (CUpointer_attribute)

Enum values:

• POINTER_ATTRIBUTE_CONTEXT - The CUcontext on which a pointer was allocated or registered
• POINTER_ATTRIBUTE_MEMORY_TYPE - The CUmemorytype describing the physical location of a pointer
• POINTER_ATTRIBUTE_DEVICE_POINTER - The address at which a pointer's memory may be accessed on the device
• POINTER_ATTRIBUTE_HOST_POINTER - The address at which a pointer's memory may be accessed on the host
• POINTER_ATTRIBUTE_P2P_TOKENS - A pair of tokens for use with the nv-p2p.h Linux kernel interface
• POINTER_ATTRIBUTE_SYNC_MEMOPS - Synchronize every synchronous memory operation initiated on this region
• POINTER_ATTRIBUTE_BUFFER_ID - A process-wide unique ID for an allocated memory region
• POINTER_ATTRIBUTE_IS_MANAGED - Indicates if the pointer points to managed memory
• POINTER_ATTRIBUTE_DEVICE_ORDINAL - A device ordinal of a device on which a pointer was allocated or registered
• POINTER_ATTRIBUTE_IS_LEGACY_CUDA_IPC_CAPABLE - 1 if this pointer maps to an allocation that is suitable for cudaIpcGetMemHandle(), 0 otherwise
• POINTER_ATTRIBUTE_RANGE_START_ADDR - Starting address for this requested pointer
• POINTER_ATTRIBUTE_RANGE_SIZE - Size of the address range for this requested pointer
• POINTER_ATTRIBUTE_MAPPED - 1 if this pointer is in a valid address range that is mapped to a backing allocation, 0 otherwise
• POINTER_ATTRIBUTE_ALLOWED_HANDLE_TYPES - Bitmask of allowed CUmemAllocationHandleType for this allocation
• POINTER_ATTRIBUTE_IS_GPU_DIRECT_RDMA_CAPABLE - 1 if the memory this pointer is referencing can be used with the GPUDirect RDMA API
• POINTER_ATTRIBUTE_ACCESS_FLAGS - Returns the access flags the device associated with the current context has on the corresponding memory referenced by the pointer given
• POINTER_ATTRIBUTE_MEMPOOL_HANDLE - Returns the mempool handle for the allocation if it was allocated from a mempool. Otherwise returns NULL.

See Also:

• Constant Field Values

CU_POINTER_ATTRIBUTE_IS_LEGACY_CUDA_IPC_CAPABLE

public static final int CU_POINTER_ATTRIBUTE_IS_LEGACY_CUDA_IPC_CAPABLE

Pointer information. (CUpointer_attribute)

Enum values:

• POINTER_ATTRIBUTE_CONTEXT - The CUcontext on which a pointer was allocated or registered
• POINTER_ATTRIBUTE_MEMORY_TYPE - The CUmemorytype describing the physical location of a pointer
• POINTER_ATTRIBUTE_DEVICE_POINTER - The address at which a pointer's memory may be accessed on the device
• POINTER_ATTRIBUTE_HOST_POINTER - The address at which a pointer's memory may be accessed on the host
• POINTER_ATTRIBUTE_P2P_TOKENS - A pair of tokens for use with the nv-p2p.h Linux kernel interface
• POINTER_ATTRIBUTE_SYNC_MEMOPS - Synchronize every synchronous memory operation initiated on this region
• POINTER_ATTRIBUTE_BUFFER_ID - A process-wide unique ID for an allocated memory region
• POINTER_ATTRIBUTE_IS_MANAGED - Indicates if the pointer points to managed memory
• POINTER_ATTRIBUTE_DEVICE_ORDINAL - A device ordinal of a device on which a pointer was allocated or registered
• POINTER_ATTRIBUTE_IS_LEGACY_CUDA_IPC_CAPABLE - 1 if this pointer maps to an allocation that is suitable for cudaIpcGetMemHandle(), 0 otherwise
• POINTER_ATTRIBUTE_RANGE_START_ADDR - Starting address for this requested pointer
• POINTER_ATTRIBUTE_RANGE_SIZE - Size of the address range for this requested pointer
• POINTER_ATTRIBUTE_MAPPED - 1 if this pointer is in a valid address range that is mapped to a backing allocation, 0 otherwise
• POINTER_ATTRIBUTE_ALLOWED_HANDLE_TYPES - Bitmask of allowed CUmemAllocationHandleType for this allocation
• POINTER_ATTRIBUTE_IS_GPU_DIRECT_RDMA_CAPABLE - 1 if the memory this pointer is referencing can be used with the GPUDirect RDMA API
• POINTER_ATTRIBUTE_ACCESS_FLAGS - Returns the access flags the device associated with the current context has on the corresponding memory referenced by the pointer given
• POINTER_ATTRIBUTE_MEMPOOL_HANDLE - Returns the mempool handle for the allocation if it was allocated from a mempool. Otherwise returns NULL.

See Also:

• Constant Field Values

CU_POINTER_ATTRIBUTE_RANGE_START_ADDR

public static final int CU_POINTER_ATTRIBUTE_RANGE_START_ADDR

Pointer information. (CUpointer_attribute)

Enum values:

• POINTER_ATTRIBUTE_CONTEXT - The CUcontext on which a pointer was allocated or registered
• POINTER_ATTRIBUTE_MEMORY_TYPE - The CUmemorytype describing the physical location of a pointer
• POINTER_ATTRIBUTE_DEVICE_POINTER - The address at which a pointer's memory may be accessed on the device
• POINTER_ATTRIBUTE_HOST_POINTER - The address at which a pointer's memory may be accessed on the host
• POINTER_ATTRIBUTE_P2P_TOKENS - A pair of tokens for use with the nv-p2p.h Linux kernel interface
• POINTER_ATTRIBUTE_SYNC_MEMOPS - Synchronize every synchronous memory operation initiated on this region
• POINTER_ATTRIBUTE_BUFFER_ID - A process-wide unique ID for an allocated memory region
• POINTER_ATTRIBUTE_IS_MANAGED - Indicates if the pointer points to managed memory
• POINTER_ATTRIBUTE_DEVICE_ORDINAL - A device ordinal of a device on which a pointer was allocated or registered
• POINTER_ATTRIBUTE_IS_LEGACY_CUDA_IPC_CAPABLE - 1 if this pointer maps to an allocation that is suitable for cudaIpcGetMemHandle(), 0 otherwise
• POINTER_ATTRIBUTE_RANGE_START_ADDR - Starting address for this requested pointer
• POINTER_ATTRIBUTE_RANGE_SIZE - Size of the address range for this requested pointer
• POINTER_ATTRIBUTE_MAPPED - 1 if this pointer is in a valid address range that is mapped to a backing allocation, 0 otherwise
• POINTER_ATTRIBUTE_ALLOWED_HANDLE_TYPES - Bitmask of allowed CUmemAllocationHandleType for this allocation
• POINTER_ATTRIBUTE_IS_GPU_DIRECT_RDMA_CAPABLE - 1 if the memory this pointer is referencing can be used with the GPUDirect RDMA API
• POINTER_ATTRIBUTE_ACCESS_FLAGS - Returns the access flags the device associated with the current context has on the corresponding memory referenced by the pointer given
• POINTER_ATTRIBUTE_MEMPOOL_HANDLE - Returns the mempool handle for the allocation if it was allocated from a mempool. Otherwise returns NULL.

See Also:

• Constant Field Values

CU_POINTER_ATTRIBUTE_RANGE_SIZE

public static final int CU_POINTER_ATTRIBUTE_RANGE_SIZE

Pointer information. (CUpointer_attribute)

Enum values:

• POINTER_ATTRIBUTE_CONTEXT - The CUcontext on which a pointer was allocated or registered
• POINTER_ATTRIBUTE_MEMORY_TYPE - The CUmemorytype describing the physical location of a pointer
• POINTER_ATTRIBUTE_DEVICE_POINTER - The address at which a pointer's memory may be accessed on the device
• POINTER_ATTRIBUTE_HOST_POINTER - The address at which a pointer's memory may be accessed on the host
• POINTER_ATTRIBUTE_P2P_TOKENS - A pair of tokens for use with the nv-p2p.h Linux kernel interface
• POINTER_ATTRIBUTE_SYNC_MEMOPS - Synchronize every synchronous memory operation initiated on this region
• POINTER_ATTRIBUTE_BUFFER_ID - A process-wide unique ID for an allocated memory region
• POINTER_ATTRIBUTE_IS_MANAGED - Indicates if the pointer points to managed memory
• POINTER_ATTRIBUTE_DEVICE_ORDINAL - A device ordinal of a device on which a pointer was allocated or registered
• POINTER_ATTRIBUTE_IS_LEGACY_CUDA_IPC_CAPABLE - 1 if this pointer maps to an allocation that is suitable for cudaIpcGetMemHandle(), 0 otherwise
• POINTER_ATTRIBUTE_RANGE_START_ADDR - Starting address for this requested pointer
• POINTER_ATTRIBUTE_RANGE_SIZE - Size of the address range for this requested pointer
• POINTER_ATTRIBUTE_MAPPED - 1 if this pointer is in a valid address range that is mapped to a backing allocation, 0 otherwise
• POINTER_ATTRIBUTE_ALLOWED_HANDLE_TYPES - Bitmask of allowed CUmemAllocationHandleType for this allocation
• POINTER_ATTRIBUTE_IS_GPU_DIRECT_RDMA_CAPABLE - 1 if the memory this pointer is referencing can be used with the GPUDirect RDMA API
• POINTER_ATTRIBUTE_ACCESS_FLAGS - Returns the access flags the device associated with the current context has on the corresponding memory referenced by the pointer given
• POINTER_ATTRIBUTE_MEMPOOL_HANDLE - Returns the mempool handle for the allocation if it was allocated from a mempool. Otherwise returns NULL.

See Also:

• Constant Field Values

CU_POINTER_ATTRIBUTE_MAPPED

public static final int CU_POINTER_ATTRIBUTE_MAPPED

Pointer information. (CUpointer_attribute)

Enum values:

• POINTER_ATTRIBUTE_CONTEXT - The CUcontext on which a pointer was allocated or registered
• POINTER_ATTRIBUTE_MEMORY_TYPE - The CUmemorytype describing the physical location of a pointer
• POINTER_ATTRIBUTE_DEVICE_POINTER - The address at which a pointer's memory may be accessed on the device
• POINTER_ATTRIBUTE_HOST_POINTER - The address at which a pointer's memory may be accessed on the host
• POINTER_ATTRIBUTE_P2P_TOKENS - A pair of tokens for use with the nv-p2p.h Linux kernel interface
• POINTER_ATTRIBUTE_SYNC_MEMOPS - Synchronize every synchronous memory operation initiated on this region
• POINTER_ATTRIBUTE_BUFFER_ID - A process-wide unique ID for an allocated memory region
• POINTER_ATTRIBUTE_IS_MANAGED - Indicates if the pointer points to managed memory
• POINTER_ATTRIBUTE_DEVICE_ORDINAL - A device ordinal of a device on which a pointer was allocated or registered
• POINTER_ATTRIBUTE_IS_LEGACY_CUDA_IPC_CAPABLE - 1 if this pointer maps to an allocation that is suitable for cudaIpcGetMemHandle(), 0 otherwise
• POINTER_ATTRIBUTE_RANGE_START_ADDR - Starting address for this requested pointer
• POINTER_ATTRIBUTE_RANGE_SIZE - Size of the address range for this requested pointer
• POINTER_ATTRIBUTE_MAPPED - 1 if this pointer is in a valid address range that is mapped to a backing allocation, 0 otherwise
• POINTER_ATTRIBUTE_ALLOWED_HANDLE_TYPES - Bitmask of allowed CUmemAllocationHandleType for this allocation
• POINTER_ATTRIBUTE_IS_GPU_DIRECT_RDMA_CAPABLE - 1 if the memory this pointer is referencing can be used with the GPUDirect RDMA API
• POINTER_ATTRIBUTE_ACCESS_FLAGS - Returns the access flags the device associated with the current context has on the corresponding memory referenced by the pointer given
• POINTER_ATTRIBUTE_MEMPOOL_HANDLE - Returns the mempool handle for the allocation if it was allocated from a mempool. Otherwise returns NULL.

See Also:

• Constant Field Values

CU_POINTER_ATTRIBUTE_ALLOWED_HANDLE_TYPES

public static final int CU_POINTER_ATTRIBUTE_ALLOWED_HANDLE_TYPES

Pointer information. (CUpointer_attribute)

Enum values:

• POINTER_ATTRIBUTE_CONTEXT - The CUcontext on which a pointer was allocated or registered
• POINTER_ATTRIBUTE_MEMORY_TYPE - The CUmemorytype describing the physical location of a pointer
• POINTER_ATTRIBUTE_DEVICE_POINTER - The address at which a pointer's memory may be accessed on the device
• POINTER_ATTRIBUTE_HOST_POINTER - The address at which a pointer's memory may be accessed on the host
• POINTER_ATTRIBUTE_P2P_TOKENS - A pair of tokens for use with the nv-p2p.h Linux kernel interface
• POINTER_ATTRIBUTE_SYNC_MEMOPS - Synchronize every synchronous memory operation initiated on this region
• POINTER_ATTRIBUTE_BUFFER_ID - A process-wide unique ID for an allocated memory region
• POINTER_ATTRIBUTE_IS_MANAGED - Indicates if the pointer points to managed memory
• POINTER_ATTRIBUTE_DEVICE_ORDINAL - A device ordinal of a device on which a pointer was allocated or registered
• POINTER_ATTRIBUTE_IS_LEGACY_CUDA_IPC_CAPABLE - 1 if this pointer maps to an allocation that is suitable for cudaIpcGetMemHandle(), 0 otherwise
• POINTER_ATTRIBUTE_RANGE_START_ADDR - Starting address for this requested pointer
• POINTER_ATTRIBUTE_RANGE_SIZE - Size of the address range for this requested pointer
• POINTER_ATTRIBUTE_MAPPED - 1 if this pointer is in a valid address range that is mapped to a backing allocation, 0 otherwise
• POINTER_ATTRIBUTE_ALLOWED_HANDLE_TYPES - Bitmask of allowed CUmemAllocationHandleType for this allocation
• POINTER_ATTRIBUTE_IS_GPU_DIRECT_RDMA_CAPABLE - 1 if the memory this pointer is referencing can be used with the GPUDirect RDMA API
• POINTER_ATTRIBUTE_ACCESS_FLAGS - Returns the access flags the device associated with the current context has on the corresponding memory referenced by the pointer given
• POINTER_ATTRIBUTE_MEMPOOL_HANDLE - Returns the mempool handle for the allocation if it was allocated from a mempool. Otherwise returns NULL.

See Also:

• Constant Field Values

CU_POINTER_ATTRIBUTE_IS_GPU_DIRECT_RDMA_CAPABLE

public static final int CU_POINTER_ATTRIBUTE_IS_GPU_DIRECT_RDMA_CAPABLE

Pointer information. (CUpointer_attribute)

Enum values:

• POINTER_ATTRIBUTE_CONTEXT - The CUcontext on which a pointer was allocated or registered
• POINTER_ATTRIBUTE_MEMORY_TYPE - The CUmemorytype describing the physical location of a pointer
• POINTER_ATTRIBUTE_DEVICE_POINTER - The address at which a pointer's memory may be accessed on the device
• POINTER_ATTRIBUTE_HOST_POINTER - The address at which a pointer's memory may be accessed on the host
• POINTER_ATTRIBUTE_P2P_TOKENS - A pair of tokens for use with the nv-p2p.h Linux kernel interface
• POINTER_ATTRIBUTE_SYNC_MEMOPS - Synchronize every synchronous memory operation initiated on this region
• POINTER_ATTRIBUTE_BUFFER_ID - A process-wide unique ID for an allocated memory region
• POINTER_ATTRIBUTE_IS_MANAGED - Indicates if the pointer points to managed memory
• POINTER_ATTRIBUTE_DEVICE_ORDINAL - A device ordinal of a device on which a pointer was allocated or registered
• POINTER_ATTRIBUTE_IS_LEGACY_CUDA_IPC_CAPABLE - 1 if this pointer maps to an allocation that is suitable for cudaIpcGetMemHandle(), 0 otherwise
• POINTER_ATTRIBUTE_RANGE_START_ADDR - Starting address for this requested pointer
• POINTER_ATTRIBUTE_RANGE_SIZE - Size of the address range for this requested pointer
• POINTER_ATTRIBUTE_MAPPED - 1 if this pointer is in a valid address range that is mapped to a backing allocation, 0 otherwise
• POINTER_ATTRIBUTE_ALLOWED_HANDLE_TYPES - Bitmask of allowed CUmemAllocationHandleType for this allocation
• POINTER_ATTRIBUTE_IS_GPU_DIRECT_RDMA_CAPABLE - 1 if the memory this pointer is referencing can be used with the GPUDirect RDMA API
• POINTER_ATTRIBUTE_ACCESS_FLAGS - Returns the access flags the device associated with the current context has on the corresponding memory referenced by the pointer given
• POINTER_ATTRIBUTE_MEMPOOL_HANDLE - Returns the mempool handle for the allocation if it was allocated from a mempool. Otherwise returns NULL.

See Also:

• Constant Field Values

CU_POINTER_ATTRIBUTE_ACCESS_FLAGS

public static final int CU_POINTER_ATTRIBUTE_ACCESS_FLAGS

Pointer information. (CUpointer_attribute)

Enum values:

• POINTER_ATTRIBUTE_CONTEXT - The CUcontext on which a pointer was allocated or registered
• POINTER_ATTRIBUTE_MEMORY_TYPE - The CUmemorytype describing the physical location of a pointer
• POINTER_ATTRIBUTE_DEVICE_POINTER - The address at which a pointer's memory may be accessed on the device
• POINTER_ATTRIBUTE_HOST_POINTER - The address at which a pointer's memory may be accessed on the host
• POINTER_ATTRIBUTE_P2P_TOKENS - A pair of tokens for use with the nv-p2p.h Linux kernel interface
• POINTER_ATTRIBUTE_SYNC_MEMOPS - Synchronize every synchronous memory operation initiated on this region
• POINTER_ATTRIBUTE_BUFFER_ID - A process-wide unique ID for an allocated memory region
• POINTER_ATTRIBUTE_IS_MANAGED - Indicates if the pointer points to managed memory
• POINTER_ATTRIBUTE_DEVICE_ORDINAL - A device ordinal of a device on which a pointer was allocated or registered
• POINTER_ATTRIBUTE_IS_LEGACY_CUDA_IPC_CAPABLE - 1 if this pointer maps to an allocation that is suitable for cudaIpcGetMemHandle(), 0 otherwise
• POINTER_ATTRIBUTE_RANGE_START_ADDR - Starting address for this requested pointer
• POINTER_ATTRIBUTE_RANGE_SIZE - Size of the address range for this requested pointer
• POINTER_ATTRIBUTE_MAPPED - 1 if this pointer is in a valid address range that is mapped to a backing allocation, 0 otherwise
• POINTER_ATTRIBUTE_ALLOWED_HANDLE_TYPES - Bitmask of allowed CUmemAllocationHandleType for this allocation
• POINTER_ATTRIBUTE_IS_GPU_DIRECT_RDMA_CAPABLE - 1 if the memory this pointer is referencing can be used with the GPUDirect RDMA API
• POINTER_ATTRIBUTE_ACCESS_FLAGS - Returns the access flags the device associated with the current context has on the corresponding memory referenced by the pointer given
• POINTER_ATTRIBUTE_MEMPOOL_HANDLE - Returns the mempool handle for the allocation if it was allocated from a mempool. Otherwise returns NULL.

See Also:

• Constant Field Values

CU_POINTER_ATTRIBUTE_MEMPOOL_HANDLE

public static final int CU_POINTER_ATTRIBUTE_MEMPOOL_HANDLE

Pointer information. (CUpointer_attribute)

Enum values:

• POINTER_ATTRIBUTE_CONTEXT - The CUcontext on which a pointer was allocated or registered
• POINTER_ATTRIBUTE_MEMORY_TYPE - The CUmemorytype describing the physical location of a pointer
• POINTER_ATTRIBUTE_DEVICE_POINTER - The address at which a pointer's memory may be accessed on the device
• POINTER_ATTRIBUTE_HOST_POINTER - The address at which a pointer's memory may be accessed on the host
• POINTER_ATTRIBUTE_P2P_TOKENS - A pair of tokens for use with the nv-p2p.h Linux kernel interface
• POINTER_ATTRIBUTE_SYNC_MEMOPS - Synchronize every synchronous memory operation initiated on this region
• POINTER_ATTRIBUTE_BUFFER_ID - A process-wide unique ID for an allocated memory region
• POINTER_ATTRIBUTE_IS_MANAGED - Indicates if the pointer points to managed memory
• POINTER_ATTRIBUTE_DEVICE_ORDINAL - A device ordinal of a device on which a pointer was allocated or registered
• POINTER_ATTRIBUTE_IS_LEGACY_CUDA_IPC_CAPABLE - 1 if this pointer maps to an allocation that is suitable for cudaIpcGetMemHandle(), 0 otherwise
• POINTER_ATTRIBUTE_RANGE_START_ADDR - Starting address for this requested pointer
• POINTER_ATTRIBUTE_RANGE_SIZE - Size of the address range for this requested pointer
• POINTER_ATTRIBUTE_MAPPED - 1 if this pointer is in a valid address range that is mapped to a backing allocation, 0 otherwise
• POINTER_ATTRIBUTE_ALLOWED_HANDLE_TYPES - Bitmask of allowed CUmemAllocationHandleType for this allocation
• POINTER_ATTRIBUTE_IS_GPU_DIRECT_RDMA_CAPABLE - 1 if the memory this pointer is referencing can be used with the GPUDirect RDMA API
• POINTER_ATTRIBUTE_ACCESS_FLAGS - Returns the access flags the device associated with the current context has on the corresponding memory referenced by the pointer given
• POINTER_ATTRIBUTE_MEMPOOL_HANDLE - Returns the mempool handle for the allocation if it was allocated from a mempool. Otherwise returns NULL.

See Also:

• Constant Field Values

CU_FUNC_ATTRIBUTE_MAX_THREADS_PER_BLOCK

public static final int CU_FUNC_ATTRIBUTE_MAX_THREADS_PER_BLOCK

Function properties. (CUfunction_attribute)

Enum values:

• FUNC_ATTRIBUTE_MAX_THREADS_PER_BLOCK - The maximum number of threads per block, beyond which a launch of the function would fail. This number depends on both the function and the device on which the function is currently loaded.
• FUNC_ATTRIBUTE_SHARED_SIZE_BYTES - The size in bytes of statically-allocated shared memory required by this function. This does not include dynamically-allocated shared memory requested by the user at runtime.
• FUNC_ATTRIBUTE_CONST_SIZE_BYTES - The size in bytes of user-allocated constant memory required by this function.
• FUNC_ATTRIBUTE_LOCAL_SIZE_BYTES - The size in bytes of local memory used by each thread of this function.
• FUNC_ATTRIBUTE_NUM_REGS - The number of registers used by each thread of this function.
• FUNC_ATTRIBUTE_PTX_VERSION - The PTX virtual architecture version for which the function was compiled.

  This value is the major PTX version * 10 + the minor PTX version, so a PTX version 1.3 function would return the value 13. Note that this may return the undefined value of 0 for cubins compiled prior to CUDA 3.0.

• FUNC_ATTRIBUTE_BINARY_VERSION - The binary architecture version for which the function was compiled.

  This value is the major binary version * 10 + the minor binary version, so a binary version 1.3 function would return the value 13. Note that this will return a value of 10 for legacy cubins that do not have a properly-encoded binary architecture version.

• FUNC_ATTRIBUTE_CACHE_MODE_CA - The attribute to indicate whether the function has been compiled with user specified option "-Xptxas --dlcm=ca" set.
• FUNC_ATTRIBUTE_MAX_DYNAMIC_SHARED_SIZE_BYTES - The maximum size in bytes of dynamically-allocated shared memory that can be used by this function.

  If the user-specified dynamic shared memory size is larger than this value, the launch will fail.

• FUNC_ATTRIBUTE_PREFERRED_SHARED_MEMORY_CARVEOUT - On devices where the L1 cache and shared memory use the same hardware resources, this sets the shared memory carveout preference, in percent of the total shared memory. Refer to DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR.

  This is only a hint, and the driver can choose a different ratio if required to execute the function.

See Also:

• Constant Field Values

CU_FUNC_ATTRIBUTE_SHARED_SIZE_BYTES

public static final int CU_FUNC_ATTRIBUTE_SHARED_SIZE_BYTES

Function properties. (CUfunction_attribute)

Enum values:

• FUNC_ATTRIBUTE_MAX_THREADS_PER_BLOCK - The maximum number of threads per block, beyond which a launch of the function would fail. This number depends on both the function and the device on which the function is currently loaded.
• FUNC_ATTRIBUTE_SHARED_SIZE_BYTES - The size in bytes of statically-allocated shared memory required by this function. This does not include dynamically-allocated shared memory requested by the user at runtime.
• FUNC_ATTRIBUTE_CONST_SIZE_BYTES - The size in bytes of user-allocated constant memory required by this function.
• FUNC_ATTRIBUTE_LOCAL_SIZE_BYTES - The size in bytes of local memory used by each thread of this function.
• FUNC_ATTRIBUTE_NUM_REGS - The number of registers used by each thread of this function.
• FUNC_ATTRIBUTE_PTX_VERSION - The PTX virtual architecture version for which the function was compiled.

  This value is the major PTX version * 10 + the minor PTX version, so a PTX version 1.3 function would return the value 13. Note that this may return the undefined value of 0 for cubins compiled prior to CUDA 3.0.

• FUNC_ATTRIBUTE_BINARY_VERSION - The binary architecture version for which the function was compiled.

  This value is the major binary version * 10 + the minor binary version, so a binary version 1.3 function would return the value 13. Note that this will return a value of 10 for legacy cubins that do not have a properly-encoded binary architecture version.

• FUNC_ATTRIBUTE_CACHE_MODE_CA - The attribute to indicate whether the function has been compiled with user specified option "-Xptxas --dlcm=ca" set.
• FUNC_ATTRIBUTE_MAX_DYNAMIC_SHARED_SIZE_BYTES - The maximum size in bytes of dynamically-allocated shared memory that can be used by this function.

  If the user-specified dynamic shared memory size is larger than this value, the launch will fail.

• FUNC_ATTRIBUTE_PREFERRED_SHARED_MEMORY_CARVEOUT - On devices where the L1 cache and shared memory use the same hardware resources, this sets the shared memory carveout preference, in percent of the total shared memory. Refer to DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR.

  This is only a hint, and the driver can choose a different ratio if required to execute the function.

See Also:

• Constant Field Values

CU_FUNC_ATTRIBUTE_CONST_SIZE_BYTES

public static final int CU_FUNC_ATTRIBUTE_CONST_SIZE_BYTES

Function properties. (CUfunction_attribute)

Enum values:

• FUNC_ATTRIBUTE_MAX_THREADS_PER_BLOCK - The maximum number of threads per block, beyond which a launch of the function would fail. This number depends on both the function and the device on which the function is currently loaded.
• FUNC_ATTRIBUTE_SHARED_SIZE_BYTES - The size in bytes of statically-allocated shared memory required by this function. This does not include dynamically-allocated shared memory requested by the user at runtime.
• FUNC_ATTRIBUTE_CONST_SIZE_BYTES - The size in bytes of user-allocated constant memory required by this function.
• FUNC_ATTRIBUTE_LOCAL_SIZE_BYTES - The size in bytes of local memory used by each thread of this function.
• FUNC_ATTRIBUTE_NUM_REGS - The number of registers used by each thread of this function.
• FUNC_ATTRIBUTE_PTX_VERSION - The PTX virtual architecture version for which the function was compiled.

  This value is the major PTX version * 10 + the minor PTX version, so a PTX version 1.3 function would return the value 13. Note that this may return the undefined value of 0 for cubins compiled prior to CUDA 3.0.

• FUNC_ATTRIBUTE_BINARY_VERSION - The binary architecture version for which the function was compiled.

  This value is the major binary version * 10 + the minor binary version, so a binary version 1.3 function would return the value 13. Note that this will return a value of 10 for legacy cubins that do not have a properly-encoded binary architecture version.

• FUNC_ATTRIBUTE_CACHE_MODE_CA - The attribute to indicate whether the function has been compiled with user specified option "-Xptxas --dlcm=ca" set.
• FUNC_ATTRIBUTE_MAX_DYNAMIC_SHARED_SIZE_BYTES - The maximum size in bytes of dynamically-allocated shared memory that can be used by this function.

  If the user-specified dynamic shared memory size is larger than this value, the launch will fail.

• FUNC_ATTRIBUTE_PREFERRED_SHARED_MEMORY_CARVEOUT - On devices where the L1 cache and shared memory use the same hardware resources, this sets the shared memory carveout preference, in percent of the total shared memory. Refer to DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR.

  This is only a hint, and the driver can choose a different ratio if required to execute the function.

See Also:

• Constant Field Values

CU_FUNC_ATTRIBUTE_LOCAL_SIZE_BYTES

public static final int CU_FUNC_ATTRIBUTE_LOCAL_SIZE_BYTES

Function properties. (CUfunction_attribute)

Enum values:

• FUNC_ATTRIBUTE_MAX_THREADS_PER_BLOCK - The maximum number of threads per block, beyond which a launch of the function would fail. This number depends on both the function and the device on which the function is currently loaded.
• FUNC_ATTRIBUTE_SHARED_SIZE_BYTES - The size in bytes of statically-allocated shared memory required by this function. This does not include dynamically-allocated shared memory requested by the user at runtime.
• FUNC_ATTRIBUTE_CONST_SIZE_BYTES - The size in bytes of user-allocated constant memory required by this function.
• FUNC_ATTRIBUTE_LOCAL_SIZE_BYTES - The size in bytes of local memory used by each thread of this function.
• FUNC_ATTRIBUTE_NUM_REGS - The number of registers used by each thread of this function.
• FUNC_ATTRIBUTE_PTX_VERSION - The PTX virtual architecture version for which the function was compiled.

  This value is the major PTX version * 10 + the minor PTX version, so a PTX version 1.3 function would return the value 13. Note that this may return the undefined value of 0 for cubins compiled prior to CUDA 3.0.

• FUNC_ATTRIBUTE_BINARY_VERSION - The binary architecture version for which the function was compiled.

  This value is the major binary version * 10 + the minor binary version, so a binary version 1.3 function would return the value 13. Note that this will return a value of 10 for legacy cubins that do not have a properly-encoded binary architecture version.

• FUNC_ATTRIBUTE_CACHE_MODE_CA - The attribute to indicate whether the function has been compiled with user specified option "-Xptxas --dlcm=ca" set.
• FUNC_ATTRIBUTE_MAX_DYNAMIC_SHARED_SIZE_BYTES - The maximum size in bytes of dynamically-allocated shared memory that can be used by this function.

  If the user-specified dynamic shared memory size is larger than this value, the launch will fail.

• FUNC_ATTRIBUTE_PREFERRED_SHARED_MEMORY_CARVEOUT - On devices where the L1 cache and shared memory use the same hardware resources, this sets the shared memory carveout preference, in percent of the total shared memory. Refer to DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR.

  This is only a hint, and the driver can choose a different ratio if required to execute the function.

See Also:

• Constant Field Values

CU_FUNC_ATTRIBUTE_NUM_REGS

public static final int CU_FUNC_ATTRIBUTE_NUM_REGS

Function properties. (CUfunction_attribute)

Enum values:

• FUNC_ATTRIBUTE_MAX_THREADS_PER_BLOCK - The maximum number of threads per block, beyond which a launch of the function would fail. This number depends on both the function and the device on which the function is currently loaded.
• FUNC_ATTRIBUTE_SHARED_SIZE_BYTES - The size in bytes of statically-allocated shared memory required by this function. This does not include dynamically-allocated shared memory requested by the user at runtime.
• FUNC_ATTRIBUTE_CONST_SIZE_BYTES - The size in bytes of user-allocated constant memory required by this function.
• FUNC_ATTRIBUTE_LOCAL_SIZE_BYTES - The size in bytes of local memory used by each thread of this function.
• FUNC_ATTRIBUTE_NUM_REGS - The number of registers used by each thread of this function.
• FUNC_ATTRIBUTE_PTX_VERSION - The PTX virtual architecture version for which the function was compiled.

  This value is the major PTX version * 10 + the minor PTX version, so a PTX version 1.3 function would return the value 13. Note that this may return the undefined value of 0 for cubins compiled prior to CUDA 3.0.

• FUNC_ATTRIBUTE_BINARY_VERSION - The binary architecture version for which the function was compiled.

  This value is the major binary version * 10 + the minor binary version, so a binary version 1.3 function would return the value 13. Note that this will return a value of 10 for legacy cubins that do not have a properly-encoded binary architecture version.

• FUNC_ATTRIBUTE_CACHE_MODE_CA - The attribute to indicate whether the function has been compiled with user specified option "-Xptxas --dlcm=ca" set.
• FUNC_ATTRIBUTE_MAX_DYNAMIC_SHARED_SIZE_BYTES - The maximum size in bytes of dynamically-allocated shared memory that can be used by this function.

  If the user-specified dynamic shared memory size is larger than this value, the launch will fail.

• FUNC_ATTRIBUTE_PREFERRED_SHARED_MEMORY_CARVEOUT - On devices where the L1 cache and shared memory use the same hardware resources, this sets the shared memory carveout preference, in percent of the total shared memory. Refer to DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR.

  This is only a hint, and the driver can choose a different ratio if required to execute the function.

See Also:

• Constant Field Values

CU_FUNC_ATTRIBUTE_PTX_VERSION

public static final int CU_FUNC_ATTRIBUTE_PTX_VERSION

Function properties. (CUfunction_attribute)

Enum values:

• FUNC_ATTRIBUTE_MAX_THREADS_PER_BLOCK - The maximum number of threads per block, beyond which a launch of the function would fail. This number depends on both the function and the device on which the function is currently loaded.
• FUNC_ATTRIBUTE_SHARED_SIZE_BYTES - The size in bytes of statically-allocated shared memory required by this function. This does not include dynamically-allocated shared memory requested by the user at runtime.
• FUNC_ATTRIBUTE_CONST_SIZE_BYTES - The size in bytes of user-allocated constant memory required by this function.
• FUNC_ATTRIBUTE_LOCAL_SIZE_BYTES - The size in bytes of local memory used by each thread of this function.
• FUNC_ATTRIBUTE_NUM_REGS - The number of registers used by each thread of this function.
• FUNC_ATTRIBUTE_PTX_VERSION - The PTX virtual architecture version for which the function was compiled.

  This value is the major PTX version * 10 + the minor PTX version, so a PTX version 1.3 function would return the value 13. Note that this may return the undefined value of 0 for cubins compiled prior to CUDA 3.0.

• FUNC_ATTRIBUTE_BINARY_VERSION - The binary architecture version for which the function was compiled.

  This value is the major binary version * 10 + the minor binary version, so a binary version 1.3 function would return the value 13. Note that this will return a value of 10 for legacy cubins that do not have a properly-encoded binary architecture version.

• FUNC_ATTRIBUTE_CACHE_MODE_CA - The attribute to indicate whether the function has been compiled with user specified option "-Xptxas --dlcm=ca" set.
• FUNC_ATTRIBUTE_MAX_DYNAMIC_SHARED_SIZE_BYTES - The maximum size in bytes of dynamically-allocated shared memory that can be used by this function.

  If the user-specified dynamic shared memory size is larger than this value, the launch will fail.

• FUNC_ATTRIBUTE_PREFERRED_SHARED_MEMORY_CARVEOUT - On devices where the L1 cache and shared memory use the same hardware resources, this sets the shared memory carveout preference, in percent of the total shared memory. Refer to DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR.

  This is only a hint, and the driver can choose a different ratio if required to execute the function.

See Also:

• Constant Field Values

CU_FUNC_ATTRIBUTE_BINARY_VERSION

public static final int CU_FUNC_ATTRIBUTE_BINARY_VERSION

Function properties. (CUfunction_attribute)

Enum values:

• FUNC_ATTRIBUTE_MAX_THREADS_PER_BLOCK - The maximum number of threads per block, beyond which a launch of the function would fail. This number depends on both the function and the device on which the function is currently loaded.
• FUNC_ATTRIBUTE_SHARED_SIZE_BYTES - The size in bytes of statically-allocated shared memory required by this function. This does not include dynamically-allocated shared memory requested by the user at runtime.
• FUNC_ATTRIBUTE_CONST_SIZE_BYTES - The size in bytes of user-allocated constant memory required by this function.
• FUNC_ATTRIBUTE_LOCAL_SIZE_BYTES - The size in bytes of local memory used by each thread of this function.
• FUNC_ATTRIBUTE_NUM_REGS - The number of registers used by each thread of this function.
• FUNC_ATTRIBUTE_PTX_VERSION - The PTX virtual architecture version for which the function was compiled.

  This value is the major PTX version * 10 + the minor PTX version, so a PTX version 1.3 function would return the value 13. Note that this may return the undefined value of 0 for cubins compiled prior to CUDA 3.0.

• FUNC_ATTRIBUTE_BINARY_VERSION - The binary architecture version for which the function was compiled.

  This value is the major binary version * 10 + the minor binary version, so a binary version 1.3 function would return the value 13. Note that this will return a value of 10 for legacy cubins that do not have a properly-encoded binary architecture version.

• FUNC_ATTRIBUTE_CACHE_MODE_CA - The attribute to indicate whether the function has been compiled with user specified option "-Xptxas --dlcm=ca" set.
• FUNC_ATTRIBUTE_MAX_DYNAMIC_SHARED_SIZE_BYTES - The maximum size in bytes of dynamically-allocated shared memory that can be used by this function.

  If the user-specified dynamic shared memory size is larger than this value, the launch will fail.

• FUNC_ATTRIBUTE_PREFERRED_SHARED_MEMORY_CARVEOUT - On devices where the L1 cache and shared memory use the same hardware resources, this sets the shared memory carveout preference, in percent of the total shared memory. Refer to DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR.

  This is only a hint, and the driver can choose a different ratio if required to execute the function.

See Also:

• Constant Field Values

CU_FUNC_ATTRIBUTE_CACHE_MODE_CA

public static final int CU_FUNC_ATTRIBUTE_CACHE_MODE_CA

Function properties. (CUfunction_attribute)

Enum values:

• FUNC_ATTRIBUTE_MAX_THREADS_PER_BLOCK - The maximum number of threads per block, beyond which a launch of the function would fail. This number depends on both the function and the device on which the function is currently loaded.
• FUNC_ATTRIBUTE_SHARED_SIZE_BYTES - The size in bytes of statically-allocated shared memory required by this function. This does not include dynamically-allocated shared memory requested by the user at runtime.
• FUNC_ATTRIBUTE_CONST_SIZE_BYTES - The size in bytes of user-allocated constant memory required by this function.
• FUNC_ATTRIBUTE_LOCAL_SIZE_BYTES - The size in bytes of local memory used by each thread of this function.
• FUNC_ATTRIBUTE_NUM_REGS - The number of registers used by each thread of this function.
• FUNC_ATTRIBUTE_PTX_VERSION - The PTX virtual architecture version for which the function was compiled.

  This value is the major PTX version * 10 + the minor PTX version, so a PTX version 1.3 function would return the value 13. Note that this may return the undefined value of 0 for cubins compiled prior to CUDA 3.0.

• FUNC_ATTRIBUTE_BINARY_VERSION - The binary architecture version for which the function was compiled.

  This value is the major binary version * 10 + the minor binary version, so a binary version 1.3 function would return the value 13. Note that this will return a value of 10 for legacy cubins that do not have a properly-encoded binary architecture version.

• FUNC_ATTRIBUTE_CACHE_MODE_CA - The attribute to indicate whether the function has been compiled with user specified option "-Xptxas --dlcm=ca" set.
• FUNC_ATTRIBUTE_MAX_DYNAMIC_SHARED_SIZE_BYTES - The maximum size in bytes of dynamically-allocated shared memory that can be used by this function.

  If the user-specified dynamic shared memory size is larger than this value, the launch will fail.

• FUNC_ATTRIBUTE_PREFERRED_SHARED_MEMORY_CARVEOUT - On devices where the L1 cache and shared memory use the same hardware resources, this sets the shared memory carveout preference, in percent of the total shared memory. Refer to DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR.

  This is only a hint, and the driver can choose a different ratio if required to execute the function.

See Also:

• Constant Field Values

CU_FUNC_ATTRIBUTE_MAX_DYNAMIC_SHARED_SIZE_BYTES

public static final int CU_FUNC_ATTRIBUTE_MAX_DYNAMIC_SHARED_SIZE_BYTES

Function properties. (CUfunction_attribute)

Enum values:

• FUNC_ATTRIBUTE_MAX_THREADS_PER_BLOCK - The maximum number of threads per block, beyond which a launch of the function would fail. This number depends on both the function and the device on which the function is currently loaded.
• FUNC_ATTRIBUTE_SHARED_SIZE_BYTES - The size in bytes of statically-allocated shared memory required by this function. This does not include dynamically-allocated shared memory requested by the user at runtime.
• FUNC_ATTRIBUTE_CONST_SIZE_BYTES - The size in bytes of user-allocated constant memory required by this function.
• FUNC_ATTRIBUTE_LOCAL_SIZE_BYTES - The size in bytes of local memory used by each thread of this function.
• FUNC_ATTRIBUTE_NUM_REGS - The number of registers used by each thread of this function.
• FUNC_ATTRIBUTE_PTX_VERSION - The PTX virtual architecture version for which the function was compiled.

  This value is the major PTX version * 10 + the minor PTX version, so a PTX version 1.3 function would return the value 13. Note that this may return the undefined value of 0 for cubins compiled prior to CUDA 3.0.

• FUNC_ATTRIBUTE_BINARY_VERSION - The binary architecture version for which the function was compiled.

  This value is the major binary version * 10 + the minor binary version, so a binary version 1.3 function would return the value 13. Note that this will return a value of 10 for legacy cubins that do not have a properly-encoded binary architecture version.

• FUNC_ATTRIBUTE_CACHE_MODE_CA - The attribute to indicate whether the function has been compiled with user specified option "-Xptxas --dlcm=ca" set.
• FUNC_ATTRIBUTE_MAX_DYNAMIC_SHARED_SIZE_BYTES - The maximum size in bytes of dynamically-allocated shared memory that can be used by this function.

  If the user-specified dynamic shared memory size is larger than this value, the launch will fail.

• FUNC_ATTRIBUTE_PREFERRED_SHARED_MEMORY_CARVEOUT - On devices where the L1 cache and shared memory use the same hardware resources, this sets the shared memory carveout preference, in percent of the total shared memory. Refer to DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR.

  This is only a hint, and the driver can choose a different ratio if required to execute the function.

See Also:

• Constant Field Values

CU_FUNC_ATTRIBUTE_PREFERRED_SHARED_MEMORY_CARVEOUT

public static final int CU_FUNC_ATTRIBUTE_PREFERRED_SHARED_MEMORY_CARVEOUT

Function properties. (CUfunction_attribute)

Enum values:

• FUNC_ATTRIBUTE_MAX_THREADS_PER_BLOCK - The maximum number of threads per block, beyond which a launch of the function would fail. This number depends on both the function and the device on which the function is currently loaded.
• FUNC_ATTRIBUTE_SHARED_SIZE_BYTES - The size in bytes of statically-allocated shared memory required by this function. This does not include dynamically-allocated shared memory requested by the user at runtime.
• FUNC_ATTRIBUTE_CONST_SIZE_BYTES - The size in bytes of user-allocated constant memory required by this function.
• FUNC_ATTRIBUTE_LOCAL_SIZE_BYTES - The size in bytes of local memory used by each thread of this function.
• FUNC_ATTRIBUTE_NUM_REGS - The number of registers used by each thread of this function.
• FUNC_ATTRIBUTE_PTX_VERSION - The PTX virtual architecture version for which the function was compiled.

  This value is the major PTX version * 10 + the minor PTX version, so a PTX version 1.3 function would return the value 13. Note that this may return the undefined value of 0 for cubins compiled prior to CUDA 3.0.

• FUNC_ATTRIBUTE_BINARY_VERSION - The binary architecture version for which the function was compiled.

  This value is the major binary version * 10 + the minor binary version, so a binary version 1.3 function would return the value 13. Note that this will return a value of 10 for legacy cubins that do not have a properly-encoded binary architecture version.

• FUNC_ATTRIBUTE_CACHE_MODE_CA - The attribute to indicate whether the function has been compiled with user specified option "-Xptxas --dlcm=ca" set.
• FUNC_ATTRIBUTE_MAX_DYNAMIC_SHARED_SIZE_BYTES - The maximum size in bytes of dynamically-allocated shared memory that can be used by this function.

  If the user-specified dynamic shared memory size is larger than this value, the launch will fail.

• FUNC_ATTRIBUTE_PREFERRED_SHARED_MEMORY_CARVEOUT - On devices where the L1 cache and shared memory use the same hardware resources, this sets the shared memory carveout preference, in percent of the total shared memory. Refer to DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR.

  This is only a hint, and the driver can choose a different ratio if required to execute the function.

See Also:

• Constant Field Values

CU_FUNC_CACHE_PREFER_NONE

public static final int CU_FUNC_CACHE_PREFER_NONE

Function cache configurations. (CUfunc_cache)

Enum values:

• FUNC_CACHE_PREFER_NONE - no preference for shared memory or L1 (default)
• FUNC_CACHE_PREFER_SHARED - prefer larger shared memory and smaller L1 cache
• FUNC_CACHE_PREFER_L1 - prefer larger L1 cache and smaller shared memory
• FUNC_CACHE_PREFER_EQUAL - prefer equal sized L1 cache and shared memory

See Also:

• Constant Field Values

CU_FUNC_CACHE_PREFER_SHARED

public static final int CU_FUNC_CACHE_PREFER_SHARED

Function cache configurations. (CUfunc_cache)

Enum values:

• FUNC_CACHE_PREFER_NONE - no preference for shared memory or L1 (default)
• FUNC_CACHE_PREFER_SHARED - prefer larger shared memory and smaller L1 cache
• FUNC_CACHE_PREFER_L1 - prefer larger L1 cache and smaller shared memory
• FUNC_CACHE_PREFER_EQUAL - prefer equal sized L1 cache and shared memory

See Also:

• Constant Field Values

CU_FUNC_CACHE_PREFER_L1

public static final int CU_FUNC_CACHE_PREFER_L1

Function cache configurations. (CUfunc_cache)

Enum values:

• FUNC_CACHE_PREFER_NONE - no preference for shared memory or L1 (default)
• FUNC_CACHE_PREFER_SHARED - prefer larger shared memory and smaller L1 cache
• FUNC_CACHE_PREFER_L1 - prefer larger L1 cache and smaller shared memory
• FUNC_CACHE_PREFER_EQUAL - prefer equal sized L1 cache and shared memory

See Also:

• Constant Field Values

CU_FUNC_CACHE_PREFER_EQUAL

public static final int CU_FUNC_CACHE_PREFER_EQUAL

Function cache configurations. (CUfunc_cache)

Enum values:

• FUNC_CACHE_PREFER_NONE - no preference for shared memory or L1 (default)
• FUNC_CACHE_PREFER_SHARED - prefer larger shared memory and smaller L1 cache
• FUNC_CACHE_PREFER_L1 - prefer larger L1 cache and smaller shared memory
• FUNC_CACHE_PREFER_EQUAL - prefer equal sized L1 cache and shared memory

See Also:

• Constant Field Values

CU_SHARED_MEM_CONFIG_DEFAULT_BANK_SIZE

public static final int CU_SHARED_MEM_CONFIG_DEFAULT_BANK_SIZE

Shared memory configurations. (CUsharedconfig)

Enum values:

• SHARED_MEM_CONFIG_DEFAULT_BANK_SIZE - set default shared memory bank size
• SHARED_MEM_CONFIG_FOUR_BYTE_BANK_SIZE - set shared memory bank width to four bytes
• SHARED_MEM_CONFIG_EIGHT_BYTE_BANK_SIZE - set shared memory bank width to eight bytes

See Also:

• Constant Field Values

CU_SHARED_MEM_CONFIG_FOUR_BYTE_BANK_SIZE

public static final int CU_SHARED_MEM_CONFIG_FOUR_BYTE_BANK_SIZE

Shared memory configurations. (CUsharedconfig)

Enum values:

• SHARED_MEM_CONFIG_DEFAULT_BANK_SIZE - set default shared memory bank size
• SHARED_MEM_CONFIG_FOUR_BYTE_BANK_SIZE - set shared memory bank width to four bytes
• SHARED_MEM_CONFIG_EIGHT_BYTE_BANK_SIZE - set shared memory bank width to eight bytes

See Also:

• Constant Field Values

CU_SHARED_MEM_CONFIG_EIGHT_BYTE_BANK_SIZE

public static final int CU_SHARED_MEM_CONFIG_EIGHT_BYTE_BANK_SIZE

Shared memory configurations. (CUsharedconfig)

Enum values:

• SHARED_MEM_CONFIG_DEFAULT_BANK_SIZE - set default shared memory bank size
• SHARED_MEM_CONFIG_FOUR_BYTE_BANK_SIZE - set shared memory bank width to four bytes
• SHARED_MEM_CONFIG_EIGHT_BYTE_BANK_SIZE - set shared memory bank width to eight bytes

See Also:

• Constant Field Values

CU_SHAREDMEM_CARVEOUT_DEFAULT

public static final int CU_SHAREDMEM_CARVEOUT_DEFAULT

Shared memory carveout configurations. (CUshared_carveout)

These may be passed to FuncSetAttribute.

Enum values:

• SHAREDMEM_CARVEOUT_DEFAULT - no preference for shared memory or L1 (default)
• SHAREDMEM_CARVEOUT_MAX_SHARED - prefer maximum available shared memory, minimum L1 cache
• SHAREDMEM_CARVEOUT_MAX_L1 - prefer maximum available L1 cache, minimum shared memory

See Also:

• Constant Field Values

CU_SHAREDMEM_CARVEOUT_MAX_SHARED

public static final int CU_SHAREDMEM_CARVEOUT_MAX_SHARED

Shared memory carveout configurations. (CUshared_carveout)

These may be passed to FuncSetAttribute.

Enum values:

• SHAREDMEM_CARVEOUT_DEFAULT - no preference for shared memory or L1 (default)
• SHAREDMEM_CARVEOUT_MAX_SHARED - prefer maximum available shared memory, minimum L1 cache
• SHAREDMEM_CARVEOUT_MAX_L1 - prefer maximum available L1 cache, minimum shared memory

See Also:

• Constant Field Values

CU_SHAREDMEM_CARVEOUT_MAX_L1

public static final int CU_SHAREDMEM_CARVEOUT_MAX_L1

Shared memory carveout configurations. (CUshared_carveout)

These may be passed to FuncSetAttribute.

Enum values:

• SHAREDMEM_CARVEOUT_DEFAULT - no preference for shared memory or L1 (default)
• SHAREDMEM_CARVEOUT_MAX_SHARED - prefer maximum available shared memory, minimum L1 cache
• SHAREDMEM_CARVEOUT_MAX_L1 - prefer maximum available L1 cache, minimum shared memory

See Also:

• Constant Field Values

CU_MEMORYTYPE_HOST

public static final int CU_MEMORYTYPE_HOST

Memory types. (CUmemorytype)

Enum values:

• MEMORYTYPE_HOST - Host memory
• MEMORYTYPE_DEVICE - Device memory
• MEMORYTYPE_ARRAY - Array memory
• MEMORYTYPE_UNIFIED - Unified device or host memory

See Also:

• Constant Field Values

CU_MEMORYTYPE_DEVICE

public static final int CU_MEMORYTYPE_DEVICE

Memory types. (CUmemorytype)

Enum values:

• MEMORYTYPE_HOST - Host memory
• MEMORYTYPE_DEVICE - Device memory
• MEMORYTYPE_ARRAY - Array memory
• MEMORYTYPE_UNIFIED - Unified device or host memory

See Also:

• Constant Field Values

CU_MEMORYTYPE_ARRAY

public static final int CU_MEMORYTYPE_ARRAY

Memory types. (CUmemorytype)

Enum values:

• MEMORYTYPE_HOST - Host memory
• MEMORYTYPE_DEVICE - Device memory
• MEMORYTYPE_ARRAY - Array memory
• MEMORYTYPE_UNIFIED - Unified device or host memory

See Also:

• Constant Field Values

CU_MEMORYTYPE_UNIFIED

public static final int CU_MEMORYTYPE_UNIFIED

Memory types. (CUmemorytype)

Enum values:

• MEMORYTYPE_HOST - Host memory
• MEMORYTYPE_DEVICE - Device memory
• MEMORYTYPE_ARRAY - Array memory
• MEMORYTYPE_UNIFIED - Unified device or host memory

See Also:

• Constant Field Values

CU_COMPUTEMODE_DEFAULT

public static final int CU_COMPUTEMODE_DEFAULT

Compute Modes. (CUcomputemode)

Enum values:

• COMPUTEMODE_DEFAULT - Default compute mode (Multiple contexts allowed per device)
• COMPUTEMODE_PROHIBITED - Compute-prohibited mode (No contexts can be created on this device at this time)
• COMPUTEMODE_EXCLUSIVE_PROCESS - Compute-exclusive-process mode (Only one context used by a single process can be present on this device at a time)

See Also:

• Constant Field Values

CU_COMPUTEMODE_PROHIBITED

public static final int CU_COMPUTEMODE_PROHIBITED

Compute Modes. (CUcomputemode)

Enum values:

• COMPUTEMODE_DEFAULT - Default compute mode (Multiple contexts allowed per device)
• COMPUTEMODE_PROHIBITED - Compute-prohibited mode (No contexts can be created on this device at this time)
• COMPUTEMODE_EXCLUSIVE_PROCESS - Compute-exclusive-process mode (Only one context used by a single process can be present on this device at a time)

See Also:

• Constant Field Values

CU_COMPUTEMODE_EXCLUSIVE_PROCESS

public static final int CU_COMPUTEMODE_EXCLUSIVE_PROCESS

Compute Modes. (CUcomputemode)

Enum values:

• COMPUTEMODE_DEFAULT - Default compute mode (Multiple contexts allowed per device)
• COMPUTEMODE_PROHIBITED - Compute-prohibited mode (No contexts can be created on this device at this time)
• COMPUTEMODE_EXCLUSIVE_PROCESS - Compute-exclusive-process mode (Only one context used by a single process can be present on this device at a time)

See Also:

• Constant Field Values

CU_MEM_ADVISE_SET_READ_MOSTLY

public static final int CU_MEM_ADVISE_SET_READ_MOSTLY

Memory advise values. (CUmem_advise)

Enum values:

• MEM_ADVISE_SET_READ_MOSTLY - Data will mostly be read and only occassionally be written to
• MEM_ADVISE_UNSET_READ_MOSTLY - Undo the effect of MEM_ADVISE_SET_READ_MOSTLY
• MEM_ADVISE_SET_PREFERRED_LOCATION - Set the preferred location for the data as the specified device
• MEM_ADVISE_UNSET_PREFERRED_LOCATION - Clear the preferred location for the data
• MEM_ADVISE_SET_ACCESSED_BY - Data will be accessed by the specified device, so prevent page faults as much as possible
• MEM_ADVISE_UNSET_ACCESSED_BY - Let the Unified Memory subsystem decide on the page faulting policy for the specified device

See Also:

• Constant Field Values

CU_MEM_ADVISE_UNSET_READ_MOSTLY

public static final int CU_MEM_ADVISE_UNSET_READ_MOSTLY

Memory advise values. (CUmem_advise)

Enum values:

• MEM_ADVISE_SET_READ_MOSTLY - Data will mostly be read and only occassionally be written to
• MEM_ADVISE_UNSET_READ_MOSTLY - Undo the effect of MEM_ADVISE_SET_READ_MOSTLY
• MEM_ADVISE_SET_PREFERRED_LOCATION - Set the preferred location for the data as the specified device
• MEM_ADVISE_UNSET_PREFERRED_LOCATION - Clear the preferred location for the data
• MEM_ADVISE_SET_ACCESSED_BY - Data will be accessed by the specified device, so prevent page faults as much as possible
• MEM_ADVISE_UNSET_ACCESSED_BY - Let the Unified Memory subsystem decide on the page faulting policy for the specified device

See Also:

• Constant Field Values

CU_MEM_ADVISE_SET_PREFERRED_LOCATION

public static final int CU_MEM_ADVISE_SET_PREFERRED_LOCATION

Memory advise values. (CUmem_advise)

Enum values:

• MEM_ADVISE_SET_READ_MOSTLY - Data will mostly be read and only occassionally be written to
• MEM_ADVISE_UNSET_READ_MOSTLY - Undo the effect of MEM_ADVISE_SET_READ_MOSTLY
• MEM_ADVISE_SET_PREFERRED_LOCATION - Set the preferred location for the data as the specified device
• MEM_ADVISE_UNSET_PREFERRED_LOCATION - Clear the preferred location for the data
• MEM_ADVISE_SET_ACCESSED_BY - Data will be accessed by the specified device, so prevent page faults as much as possible
• MEM_ADVISE_UNSET_ACCESSED_BY - Let the Unified Memory subsystem decide on the page faulting policy for the specified device

See Also:

• Constant Field Values

CU_MEM_ADVISE_UNSET_PREFERRED_LOCATION

public static final int CU_MEM_ADVISE_UNSET_PREFERRED_LOCATION

Memory advise values. (CUmem_advise)

Enum values:

• MEM_ADVISE_SET_READ_MOSTLY - Data will mostly be read and only occassionally be written to
• MEM_ADVISE_UNSET_READ_MOSTLY - Undo the effect of MEM_ADVISE_SET_READ_MOSTLY
• MEM_ADVISE_SET_PREFERRED_LOCATION - Set the preferred location for the data as the specified device
• MEM_ADVISE_UNSET_PREFERRED_LOCATION - Clear the preferred location for the data
• MEM_ADVISE_SET_ACCESSED_BY - Data will be accessed by the specified device, so prevent page faults as much as possible
• MEM_ADVISE_UNSET_ACCESSED_BY - Let the Unified Memory subsystem decide on the page faulting policy for the specified device

See Also:

• Constant Field Values

CU_MEM_ADVISE_SET_ACCESSED_BY

public static final int CU_MEM_ADVISE_SET_ACCESSED_BY

Memory advise values. (CUmem_advise)

Enum values:

• MEM_ADVISE_SET_READ_MOSTLY - Data will mostly be read and only occassionally be written to
• MEM_ADVISE_UNSET_READ_MOSTLY - Undo the effect of MEM_ADVISE_SET_READ_MOSTLY
• MEM_ADVISE_SET_PREFERRED_LOCATION - Set the preferred location for the data as the specified device
• MEM_ADVISE_UNSET_PREFERRED_LOCATION - Clear the preferred location for the data
• MEM_ADVISE_SET_ACCESSED_BY - Data will be accessed by the specified device, so prevent page faults as much as possible
• MEM_ADVISE_UNSET_ACCESSED_BY - Let the Unified Memory subsystem decide on the page faulting policy for the specified device

See Also:

• Constant Field Values

CU_MEM_ADVISE_UNSET_ACCESSED_BY

public static final int CU_MEM_ADVISE_UNSET_ACCESSED_BY

Memory advise values. (CUmem_advise)

Enum values:

• MEM_ADVISE_SET_READ_MOSTLY - Data will mostly be read and only occassionally be written to
• MEM_ADVISE_UNSET_READ_MOSTLY - Undo the effect of MEM_ADVISE_SET_READ_MOSTLY
• MEM_ADVISE_SET_PREFERRED_LOCATION - Set the preferred location for the data as the specified device
• MEM_ADVISE_UNSET_PREFERRED_LOCATION - Clear the preferred location for the data
• MEM_ADVISE_SET_ACCESSED_BY - Data will be accessed by the specified device, so prevent page faults as much as possible
• MEM_ADVISE_UNSET_ACCESSED_BY - Let the Unified Memory subsystem decide on the page faulting policy for the specified device

See Also:

• Constant Field Values

CU_MEM_RANGE_ATTRIBUTE_READ_MOSTLY

public static final int CU_MEM_RANGE_ATTRIBUTE_READ_MOSTLY

(CUmem_range_attribute)

Enum values:

• MEM_RANGE_ATTRIBUTE_READ_MOSTLY - Whether the range will mostly be read and only occassionally be written to
• MEM_RANGE_ATTRIBUTE_PREFERRED_LOCATION - The preferred location of the range
• MEM_RANGE_ATTRIBUTE_ACCESSED_BY - Memory range has MEM_ADVISE_SET_ACCESSED_BY set for specified device
• MEM_RANGE_ATTRIBUTE_LAST_PREFETCH_LOCATION - The last location to which the range was prefetched

See Also:

• Constant Field Values

CU_MEM_RANGE_ATTRIBUTE_PREFERRED_LOCATION

public static final int CU_MEM_RANGE_ATTRIBUTE_PREFERRED_LOCATION

(CUmem_range_attribute)

Enum values:

• MEM_RANGE_ATTRIBUTE_READ_MOSTLY - Whether the range will mostly be read and only occassionally be written to
• MEM_RANGE_ATTRIBUTE_PREFERRED_LOCATION - The preferred location of the range
• MEM_RANGE_ATTRIBUTE_ACCESSED_BY - Memory range has MEM_ADVISE_SET_ACCESSED_BY set for specified device
• MEM_RANGE_ATTRIBUTE_LAST_PREFETCH_LOCATION - The last location to which the range was prefetched

See Also:

• Constant Field Values

CU_MEM_RANGE_ATTRIBUTE_ACCESSED_BY

public static final int CU_MEM_RANGE_ATTRIBUTE_ACCESSED_BY

(CUmem_range_attribute)

Enum values:

• MEM_RANGE_ATTRIBUTE_READ_MOSTLY - Whether the range will mostly be read and only occassionally be written to
• MEM_RANGE_ATTRIBUTE_PREFERRED_LOCATION - The preferred location of the range
• MEM_RANGE_ATTRIBUTE_ACCESSED_BY - Memory range has MEM_ADVISE_SET_ACCESSED_BY set for specified device
• MEM_RANGE_ATTRIBUTE_LAST_PREFETCH_LOCATION - The last location to which the range was prefetched

See Also:

• Constant Field Values

CU_MEM_RANGE_ATTRIBUTE_LAST_PREFETCH_LOCATION

public static final int CU_MEM_RANGE_ATTRIBUTE_LAST_PREFETCH_LOCATION

(CUmem_range_attribute)

Enum values:

• MEM_RANGE_ATTRIBUTE_READ_MOSTLY - Whether the range will mostly be read and only occassionally be written to
• MEM_RANGE_ATTRIBUTE_PREFERRED_LOCATION - The preferred location of the range
• MEM_RANGE_ATTRIBUTE_ACCESSED_BY - Memory range has MEM_ADVISE_SET_ACCESSED_BY set for specified device
• MEM_RANGE_ATTRIBUTE_LAST_PREFETCH_LOCATION - The last location to which the range was prefetched

See Also:

• Constant Field Values

CU_JIT_MAX_REGISTERS

public static final int CU_JIT_MAX_REGISTERS

Online compiler and linker options. (CUjit_option)

Enum values:

• JIT_MAX_REGISTERS - Max number of registers that a thread may use.

  Option type: unsigned int. Applies to: compiler only

• JIT_THREADS_PER_BLOCK - IN: Specifies minimum number of threads per block to target compilation for

  OUT: Returns the number of threads the compiler actually targeted.

  This restricts the resource utilization fo the compiler (e.g. max registers) such that a block with the given number of threads should be able to launch based on register limitations. Note, this option does not currently take into account any other resource limitations, such as shared memory utilization.

  Cannot be combined with JIT_TARGET. Option type: unsigned int. Applies to: compiler only

• JIT_WALL_TIME - Overwrites the option value with the total wall clock time, in milliseconds, spent in the compiler and linker.

  Option type: float. Applies to: compiler and linker

• JIT_INFO_LOG_BUFFER - Pointer to a buffer in which to print any log messages that are informational in nature (the buffer size is specified via option JIT_INFO_LOG_BUFFER_SIZE_BYTES).

  Option type: char *. Applies to: compiler and linker

• JIT_INFO_LOG_BUFFER_SIZE_BYTES - IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).

  OUT: Amount of log buffer filled with messages.

  Option type: unsigned int. Applies to: compiler and linker

• JIT_ERROR_LOG_BUFFER - Pointer to a buffer in which to print any log messages that reflect errors (the buffer size is specified via option JIT_ERROR_LOG_BUFFER_SIZE_BYTES).

  Option type: char *. Applies to: compiler and linker

• JIT_ERROR_LOG_BUFFER_SIZE_BYTES - IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).

  OUT: Amount of log buffer filled with messages.

  Option type: unsigned int. Applies to: compiler and linker

• JIT_OPTIMIZATION_LEVEL - Level of optimizations to apply to generated code (0 - 4), with 4 being the default and highest level of optimizations.

  Option type: unsigned int. Applies to: compiler only

• JIT_TARGET_FROM_CUCONTEXT - No option value required. Determines the target based on the current attached context (default).

  Option type: No option value needed. Applies to: compiler and linker

• JIT_TARGET - Target is chosen based on supplied CUjit_target. Cannot be combined with JIT_THREADS_PER_BLOCK.

  Option type: unsigned int for enumerated type CUjit_target. Applies to: compiler and linker

• JIT_FALLBACK_STRATEGY - Specifies choice of fallback strategy if matching cubin is not found.

  Choice is based on supplied CUjit_fallback. This option cannot be used with cuLink* APIs as the linker requires exact matches.

  Option type: unsigned int for enumerated type CUjit_fallback. Applies to: compiler only

• JIT_GENERATE_DEBUG_INFO - Specifies whether to create debug information in output (-g) (0: false, default).

  Option type: int. Applies to: compiler and linker

• JIT_LOG_VERBOSE - Generate verbose log messages (0: false, default).

  Option type: int. Applies to: compiler and linker

• JIT_GENERATE_LINE_INFO - Generate line number information (-lineinfo) (0: false, default).

  Option type: int. Applies to: compiler only

• JIT_CACHE_MODE - Specifies whether to enable caching explicitly (-dlcm). Choice is based on supplied CUjit_cacheMode_enum.

  Option type: unsigned int for enumerated type CUjit_cacheMode_enum. Applies to: compiler only

• JIT_NEW_SM3X_OPT - Used for internal purposes only, in this version of CUDA.
• JIT_FAST_COMPILE - Used for internal purposes only, in this version of CUDA.
• JIT_GLOBAL_SYMBOL_NAMES - Array of device symbol names that will be relocated to the corresponing host addresses stored in JIT_GLOBAL_SYMBOL_ADDRESSES.

  Must contain JIT_GLOBAL_SYMBOL_COUNT entries. When loding a device module, driver will relocate all encountered unresolved symbols to the host addresses. It is only allowed to register symbols that correspond to unresolved global variables. It is illegal to register the same device symbol at multiple addresses.

  Option type: const char **. Applies to: dynamic linker only

• JIT_GLOBAL_SYMBOL_ADDRESSES - Array of host addresses that will be used to relocate corresponding device symbols stored in JIT_GLOBAL_SYMBOL_NAMES.

  Must contain JIT_GLOBAL_SYMBOL_COUNT entries.

  Option type: void **. Applies to: dynamic linker only

• JIT_GLOBAL_SYMBOL_COUNT - Number of entries in JIT_GLOBAL_SYMBOL_NAMES and JIT_GLOBAL_SYMBOL_ADDRESSES arrays.

  Option type: unsigned int. Applies to: dynamic linker only

• JIT_LTO - Enable link-time optimization (-dlto) for device code (0: false, default)

  Option type: int. Applies to: compiler and linker

• JIT_FTZ - Control single-precision denormals (-ftz) support (0: false, default).
  • 1 : flushes denormal values to zero
  • 0 : preserves denormal values

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_PREC_DIV - Control single-precision floating-point division and reciprocals (-prec-div) support (1: true, default).
  • 1 : Enables the IEEE round-to-nearest mode
  • 0 : Enables the fast approximation mode

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_PREC_SQRT - Control single-precision floating-point square root (-prec-sqrt) support (1: true, default).
  • 1 : Enables the IEEE round-to-nearest mode
  • 0 : Enables the fast approximation mode

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_FMA - Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_NUM_OPTIONS - Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

See Also:

• Constant Field Values

CU_JIT_THREADS_PER_BLOCK

public static final int CU_JIT_THREADS_PER_BLOCK

Online compiler and linker options. (CUjit_option)

Enum values:

• JIT_MAX_REGISTERS - Max number of registers that a thread may use.

  Option type: unsigned int. Applies to: compiler only

• JIT_THREADS_PER_BLOCK - IN: Specifies minimum number of threads per block to target compilation for

  OUT: Returns the number of threads the compiler actually targeted.

  This restricts the resource utilization fo the compiler (e.g. max registers) such that a block with the given number of threads should be able to launch based on register limitations. Note, this option does not currently take into account any other resource limitations, such as shared memory utilization.

  Cannot be combined with JIT_TARGET. Option type: unsigned int. Applies to: compiler only

• JIT_WALL_TIME - Overwrites the option value with the total wall clock time, in milliseconds, spent in the compiler and linker.

  Option type: float. Applies to: compiler and linker

• JIT_INFO_LOG_BUFFER - Pointer to a buffer in which to print any log messages that are informational in nature (the buffer size is specified via option JIT_INFO_LOG_BUFFER_SIZE_BYTES).

  Option type: char *. Applies to: compiler and linker

• JIT_INFO_LOG_BUFFER_SIZE_BYTES - IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).

  OUT: Amount of log buffer filled with messages.

  Option type: unsigned int. Applies to: compiler and linker

• JIT_ERROR_LOG_BUFFER - Pointer to a buffer in which to print any log messages that reflect errors (the buffer size is specified via option JIT_ERROR_LOG_BUFFER_SIZE_BYTES).

  Option type: char *. Applies to: compiler and linker

• JIT_ERROR_LOG_BUFFER_SIZE_BYTES - IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).

  OUT: Amount of log buffer filled with messages.

  Option type: unsigned int. Applies to: compiler and linker

• JIT_OPTIMIZATION_LEVEL - Level of optimizations to apply to generated code (0 - 4), with 4 being the default and highest level of optimizations.

  Option type: unsigned int. Applies to: compiler only

• JIT_TARGET_FROM_CUCONTEXT - No option value required. Determines the target based on the current attached context (default).

  Option type: No option value needed. Applies to: compiler and linker

• JIT_TARGET - Target is chosen based on supplied CUjit_target. Cannot be combined with JIT_THREADS_PER_BLOCK.

  Option type: unsigned int for enumerated type CUjit_target. Applies to: compiler and linker

• JIT_FALLBACK_STRATEGY - Specifies choice of fallback strategy if matching cubin is not found.

  Choice is based on supplied CUjit_fallback. This option cannot be used with cuLink* APIs as the linker requires exact matches.

  Option type: unsigned int for enumerated type CUjit_fallback. Applies to: compiler only

• JIT_GENERATE_DEBUG_INFO - Specifies whether to create debug information in output (-g) (0: false, default).

  Option type: int. Applies to: compiler and linker

• JIT_LOG_VERBOSE - Generate verbose log messages (0: false, default).

  Option type: int. Applies to: compiler and linker

• JIT_GENERATE_LINE_INFO - Generate line number information (-lineinfo) (0: false, default).

  Option type: int. Applies to: compiler only

• JIT_CACHE_MODE - Specifies whether to enable caching explicitly (-dlcm). Choice is based on supplied CUjit_cacheMode_enum.

  Option type: unsigned int for enumerated type CUjit_cacheMode_enum. Applies to: compiler only

• JIT_NEW_SM3X_OPT - Used for internal purposes only, in this version of CUDA.
• JIT_FAST_COMPILE - Used for internal purposes only, in this version of CUDA.
• JIT_GLOBAL_SYMBOL_NAMES - Array of device symbol names that will be relocated to the corresponing host addresses stored in JIT_GLOBAL_SYMBOL_ADDRESSES.

  Must contain JIT_GLOBAL_SYMBOL_COUNT entries. When loding a device module, driver will relocate all encountered unresolved symbols to the host addresses. It is only allowed to register symbols that correspond to unresolved global variables. It is illegal to register the same device symbol at multiple addresses.

  Option type: const char **. Applies to: dynamic linker only

• JIT_GLOBAL_SYMBOL_ADDRESSES - Array of host addresses that will be used to relocate corresponding device symbols stored in JIT_GLOBAL_SYMBOL_NAMES.

  Must contain JIT_GLOBAL_SYMBOL_COUNT entries.

  Option type: void **. Applies to: dynamic linker only

• JIT_GLOBAL_SYMBOL_COUNT - Number of entries in JIT_GLOBAL_SYMBOL_NAMES and JIT_GLOBAL_SYMBOL_ADDRESSES arrays.

  Option type: unsigned int. Applies to: dynamic linker only

• JIT_LTO - Enable link-time optimization (-dlto) for device code (0: false, default)

  Option type: int. Applies to: compiler and linker

• JIT_FTZ - Control single-precision denormals (-ftz) support (0: false, default).
  • 1 : flushes denormal values to zero
  • 0 : preserves denormal values

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_PREC_DIV - Control single-precision floating-point division and reciprocals (-prec-div) support (1: true, default).
  • 1 : Enables the IEEE round-to-nearest mode
  • 0 : Enables the fast approximation mode

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_PREC_SQRT - Control single-precision floating-point square root (-prec-sqrt) support (1: true, default).
  • 1 : Enables the IEEE round-to-nearest mode
  • 0 : Enables the fast approximation mode

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_FMA - Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_NUM_OPTIONS - Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

See Also:

• Constant Field Values

CU_JIT_WALL_TIME

public static final int CU_JIT_WALL_TIME

Online compiler and linker options. (CUjit_option)

Enum values:

• JIT_MAX_REGISTERS - Max number of registers that a thread may use.

  Option type: unsigned int. Applies to: compiler only

• JIT_THREADS_PER_BLOCK - IN: Specifies minimum number of threads per block to target compilation for

  OUT: Returns the number of threads the compiler actually targeted.

  This restricts the resource utilization fo the compiler (e.g. max registers) such that a block with the given number of threads should be able to launch based on register limitations. Note, this option does not currently take into account any other resource limitations, such as shared memory utilization.

  Cannot be combined with JIT_TARGET. Option type: unsigned int. Applies to: compiler only

• JIT_WALL_TIME - Overwrites the option value with the total wall clock time, in milliseconds, spent in the compiler and linker.

  Option type: float. Applies to: compiler and linker

• JIT_INFO_LOG_BUFFER - Pointer to a buffer in which to print any log messages that are informational in nature (the buffer size is specified via option JIT_INFO_LOG_BUFFER_SIZE_BYTES).

  Option type: char *. Applies to: compiler and linker

• JIT_INFO_LOG_BUFFER_SIZE_BYTES - IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).

  OUT: Amount of log buffer filled with messages.

  Option type: unsigned int. Applies to: compiler and linker

• JIT_ERROR_LOG_BUFFER - Pointer to a buffer in which to print any log messages that reflect errors (the buffer size is specified via option JIT_ERROR_LOG_BUFFER_SIZE_BYTES).

  Option type: char *. Applies to: compiler and linker

• JIT_ERROR_LOG_BUFFER_SIZE_BYTES - IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).

  OUT: Amount of log buffer filled with messages.

  Option type: unsigned int. Applies to: compiler and linker

• JIT_OPTIMIZATION_LEVEL - Level of optimizations to apply to generated code (0 - 4), with 4 being the default and highest level of optimizations.

  Option type: unsigned int. Applies to: compiler only

• JIT_TARGET_FROM_CUCONTEXT - No option value required. Determines the target based on the current attached context (default).

  Option type: No option value needed. Applies to: compiler and linker

• JIT_TARGET - Target is chosen based on supplied CUjit_target. Cannot be combined with JIT_THREADS_PER_BLOCK.

  Option type: unsigned int for enumerated type CUjit_target. Applies to: compiler and linker

• JIT_FALLBACK_STRATEGY - Specifies choice of fallback strategy if matching cubin is not found.

  Choice is based on supplied CUjit_fallback. This option cannot be used with cuLink* APIs as the linker requires exact matches.

  Option type: unsigned int for enumerated type CUjit_fallback. Applies to: compiler only

• JIT_GENERATE_DEBUG_INFO - Specifies whether to create debug information in output (-g) (0: false, default).

  Option type: int. Applies to: compiler and linker

• JIT_LOG_VERBOSE - Generate verbose log messages (0: false, default).

  Option type: int. Applies to: compiler and linker

• JIT_GENERATE_LINE_INFO - Generate line number information (-lineinfo) (0: false, default).

  Option type: int. Applies to: compiler only

• JIT_CACHE_MODE - Specifies whether to enable caching explicitly (-dlcm). Choice is based on supplied CUjit_cacheMode_enum.

  Option type: unsigned int for enumerated type CUjit_cacheMode_enum. Applies to: compiler only

• JIT_NEW_SM3X_OPT - Used for internal purposes only, in this version of CUDA.
• JIT_FAST_COMPILE - Used for internal purposes only, in this version of CUDA.
• JIT_GLOBAL_SYMBOL_NAMES - Array of device symbol names that will be relocated to the corresponing host addresses stored in JIT_GLOBAL_SYMBOL_ADDRESSES.

  Must contain JIT_GLOBAL_SYMBOL_COUNT entries. When loding a device module, driver will relocate all encountered unresolved symbols to the host addresses. It is only allowed to register symbols that correspond to unresolved global variables. It is illegal to register the same device symbol at multiple addresses.

  Option type: const char **. Applies to: dynamic linker only

• JIT_GLOBAL_SYMBOL_ADDRESSES - Array of host addresses that will be used to relocate corresponding device symbols stored in JIT_GLOBAL_SYMBOL_NAMES.

  Must contain JIT_GLOBAL_SYMBOL_COUNT entries.

  Option type: void **. Applies to: dynamic linker only

• JIT_GLOBAL_SYMBOL_COUNT - Number of entries in JIT_GLOBAL_SYMBOL_NAMES and JIT_GLOBAL_SYMBOL_ADDRESSES arrays.

  Option type: unsigned int. Applies to: dynamic linker only

• JIT_LTO - Enable link-time optimization (-dlto) for device code (0: false, default)

  Option type: int. Applies to: compiler and linker

• JIT_FTZ - Control single-precision denormals (-ftz) support (0: false, default).
  • 1 : flushes denormal values to zero
  • 0 : preserves denormal values

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_PREC_DIV - Control single-precision floating-point division and reciprocals (-prec-div) support (1: true, default).
  • 1 : Enables the IEEE round-to-nearest mode
  • 0 : Enables the fast approximation mode

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_PREC_SQRT - Control single-precision floating-point square root (-prec-sqrt) support (1: true, default).
  • 1 : Enables the IEEE round-to-nearest mode
  • 0 : Enables the fast approximation mode

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_FMA - Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_NUM_OPTIONS - Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

See Also:

• Constant Field Values

CU_JIT_INFO_LOG_BUFFER

public static final int CU_JIT_INFO_LOG_BUFFER

Online compiler and linker options. (CUjit_option)

Enum values:

• JIT_MAX_REGISTERS - Max number of registers that a thread may use.

  Option type: unsigned int. Applies to: compiler only

• JIT_THREADS_PER_BLOCK - IN: Specifies minimum number of threads per block to target compilation for

  OUT: Returns the number of threads the compiler actually targeted.

  This restricts the resource utilization fo the compiler (e.g. max registers) such that a block with the given number of threads should be able to launch based on register limitations. Note, this option does not currently take into account any other resource limitations, such as shared memory utilization.

  Cannot be combined with JIT_TARGET. Option type: unsigned int. Applies to: compiler only

• JIT_WALL_TIME - Overwrites the option value with the total wall clock time, in milliseconds, spent in the compiler and linker.

  Option type: float. Applies to: compiler and linker

• JIT_INFO_LOG_BUFFER - Pointer to a buffer in which to print any log messages that are informational in nature (the buffer size is specified via option JIT_INFO_LOG_BUFFER_SIZE_BYTES).

  Option type: char *. Applies to: compiler and linker

• JIT_INFO_LOG_BUFFER_SIZE_BYTES - IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).

  OUT: Amount of log buffer filled with messages.

  Option type: unsigned int. Applies to: compiler and linker

• JIT_ERROR_LOG_BUFFER - Pointer to a buffer in which to print any log messages that reflect errors (the buffer size is specified via option JIT_ERROR_LOG_BUFFER_SIZE_BYTES).

  Option type: char *. Applies to: compiler and linker

• JIT_ERROR_LOG_BUFFER_SIZE_BYTES - IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).

  OUT: Amount of log buffer filled with messages.

  Option type: unsigned int. Applies to: compiler and linker

• JIT_OPTIMIZATION_LEVEL - Level of optimizations to apply to generated code (0 - 4), with 4 being the default and highest level of optimizations.

  Option type: unsigned int. Applies to: compiler only

• JIT_TARGET_FROM_CUCONTEXT - No option value required. Determines the target based on the current attached context (default).

  Option type: No option value needed. Applies to: compiler and linker

• JIT_TARGET - Target is chosen based on supplied CUjit_target. Cannot be combined with JIT_THREADS_PER_BLOCK.

  Option type: unsigned int for enumerated type CUjit_target. Applies to: compiler and linker

• JIT_FALLBACK_STRATEGY - Specifies choice of fallback strategy if matching cubin is not found.

  Choice is based on supplied CUjit_fallback. This option cannot be used with cuLink* APIs as the linker requires exact matches.

  Option type: unsigned int for enumerated type CUjit_fallback. Applies to: compiler only

• JIT_GENERATE_DEBUG_INFO - Specifies whether to create debug information in output (-g) (0: false, default).

  Option type: int. Applies to: compiler and linker

• JIT_LOG_VERBOSE - Generate verbose log messages (0: false, default).

  Option type: int. Applies to: compiler and linker

• JIT_GENERATE_LINE_INFO - Generate line number information (-lineinfo) (0: false, default).

  Option type: int. Applies to: compiler only

• JIT_CACHE_MODE - Specifies whether to enable caching explicitly (-dlcm). Choice is based on supplied CUjit_cacheMode_enum.

  Option type: unsigned int for enumerated type CUjit_cacheMode_enum. Applies to: compiler only

• JIT_NEW_SM3X_OPT - Used for internal purposes only, in this version of CUDA.
• JIT_FAST_COMPILE - Used for internal purposes only, in this version of CUDA.
• JIT_GLOBAL_SYMBOL_NAMES - Array of device symbol names that will be relocated to the corresponing host addresses stored in JIT_GLOBAL_SYMBOL_ADDRESSES.

  Must contain JIT_GLOBAL_SYMBOL_COUNT entries. When loding a device module, driver will relocate all encountered unresolved symbols to the host addresses. It is only allowed to register symbols that correspond to unresolved global variables. It is illegal to register the same device symbol at multiple addresses.

  Option type: const char **. Applies to: dynamic linker only

• JIT_GLOBAL_SYMBOL_ADDRESSES - Array of host addresses that will be used to relocate corresponding device symbols stored in JIT_GLOBAL_SYMBOL_NAMES.

  Must contain JIT_GLOBAL_SYMBOL_COUNT entries.

  Option type: void **. Applies to: dynamic linker only

• JIT_GLOBAL_SYMBOL_COUNT - Number of entries in JIT_GLOBAL_SYMBOL_NAMES and JIT_GLOBAL_SYMBOL_ADDRESSES arrays.

  Option type: unsigned int. Applies to: dynamic linker only

• JIT_LTO - Enable link-time optimization (-dlto) for device code (0: false, default)

  Option type: int. Applies to: compiler and linker

• JIT_FTZ - Control single-precision denormals (-ftz) support (0: false, default).
  • 1 : flushes denormal values to zero
  • 0 : preserves denormal values

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_PREC_DIV - Control single-precision floating-point division and reciprocals (-prec-div) support (1: true, default).
  • 1 : Enables the IEEE round-to-nearest mode
  • 0 : Enables the fast approximation mode

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_PREC_SQRT - Control single-precision floating-point square root (-prec-sqrt) support (1: true, default).
  • 1 : Enables the IEEE round-to-nearest mode
  • 0 : Enables the fast approximation mode

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_FMA - Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_NUM_OPTIONS - Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

See Also:

• Constant Field Values

CU_JIT_INFO_LOG_BUFFER_SIZE_BYTES

public static final int CU_JIT_INFO_LOG_BUFFER_SIZE_BYTES

Online compiler and linker options. (CUjit_option)

Enum values:

• JIT_MAX_REGISTERS - Max number of registers that a thread may use.

  Option type: unsigned int. Applies to: compiler only

• JIT_THREADS_PER_BLOCK - IN: Specifies minimum number of threads per block to target compilation for

  OUT: Returns the number of threads the compiler actually targeted.

  This restricts the resource utilization fo the compiler (e.g. max registers) such that a block with the given number of threads should be able to launch based on register limitations. Note, this option does not currently take into account any other resource limitations, such as shared memory utilization.

  Cannot be combined with JIT_TARGET. Option type: unsigned int. Applies to: compiler only

• JIT_WALL_TIME - Overwrites the option value with the total wall clock time, in milliseconds, spent in the compiler and linker.

  Option type: float. Applies to: compiler and linker

• JIT_INFO_LOG_BUFFER - Pointer to a buffer in which to print any log messages that are informational in nature (the buffer size is specified via option JIT_INFO_LOG_BUFFER_SIZE_BYTES).

  Option type: char *. Applies to: compiler and linker

• JIT_INFO_LOG_BUFFER_SIZE_BYTES - IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).

  OUT: Amount of log buffer filled with messages.

  Option type: unsigned int. Applies to: compiler and linker

• JIT_ERROR_LOG_BUFFER - Pointer to a buffer in which to print any log messages that reflect errors (the buffer size is specified via option JIT_ERROR_LOG_BUFFER_SIZE_BYTES).

  Option type: char *. Applies to: compiler and linker

• JIT_ERROR_LOG_BUFFER_SIZE_BYTES - IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).

  OUT: Amount of log buffer filled with messages.

  Option type: unsigned int. Applies to: compiler and linker

• JIT_OPTIMIZATION_LEVEL - Level of optimizations to apply to generated code (0 - 4), with 4 being the default and highest level of optimizations.

  Option type: unsigned int. Applies to: compiler only

• JIT_TARGET_FROM_CUCONTEXT - No option value required. Determines the target based on the current attached context (default).

  Option type: No option value needed. Applies to: compiler and linker

• JIT_TARGET - Target is chosen based on supplied CUjit_target. Cannot be combined with JIT_THREADS_PER_BLOCK.

  Option type: unsigned int for enumerated type CUjit_target. Applies to: compiler and linker

• JIT_FALLBACK_STRATEGY - Specifies choice of fallback strategy if matching cubin is not found.

  Choice is based on supplied CUjit_fallback. This option cannot be used with cuLink* APIs as the linker requires exact matches.

  Option type: unsigned int for enumerated type CUjit_fallback. Applies to: compiler only

• JIT_GENERATE_DEBUG_INFO - Specifies whether to create debug information in output (-g) (0: false, default).

  Option type: int. Applies to: compiler and linker

• JIT_LOG_VERBOSE - Generate verbose log messages (0: false, default).

  Option type: int. Applies to: compiler and linker

• JIT_GENERATE_LINE_INFO - Generate line number information (-lineinfo) (0: false, default).

  Option type: int. Applies to: compiler only

• JIT_CACHE_MODE - Specifies whether to enable caching explicitly (-dlcm). Choice is based on supplied CUjit_cacheMode_enum.

  Option type: unsigned int for enumerated type CUjit_cacheMode_enum. Applies to: compiler only

• JIT_NEW_SM3X_OPT - Used for internal purposes only, in this version of CUDA.
• JIT_FAST_COMPILE - Used for internal purposes only, in this version of CUDA.
• JIT_GLOBAL_SYMBOL_NAMES - Array of device symbol names that will be relocated to the corresponing host addresses stored in JIT_GLOBAL_SYMBOL_ADDRESSES.

  Must contain JIT_GLOBAL_SYMBOL_COUNT entries. When loding a device module, driver will relocate all encountered unresolved symbols to the host addresses. It is only allowed to register symbols that correspond to unresolved global variables. It is illegal to register the same device symbol at multiple addresses.

  Option type: const char **. Applies to: dynamic linker only

• JIT_GLOBAL_SYMBOL_ADDRESSES - Array of host addresses that will be used to relocate corresponding device symbols stored in JIT_GLOBAL_SYMBOL_NAMES.

  Must contain JIT_GLOBAL_SYMBOL_COUNT entries.

  Option type: void **. Applies to: dynamic linker only

• JIT_GLOBAL_SYMBOL_COUNT - Number of entries in JIT_GLOBAL_SYMBOL_NAMES and JIT_GLOBAL_SYMBOL_ADDRESSES arrays.

  Option type: unsigned int. Applies to: dynamic linker only

• JIT_LTO - Enable link-time optimization (-dlto) for device code (0: false, default)

  Option type: int. Applies to: compiler and linker

• JIT_FTZ - Control single-precision denormals (-ftz) support (0: false, default).
  • 1 : flushes denormal values to zero
  • 0 : preserves denormal values

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_PREC_DIV - Control single-precision floating-point division and reciprocals (-prec-div) support (1: true, default).
  • 1 : Enables the IEEE round-to-nearest mode
  • 0 : Enables the fast approximation mode

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_PREC_SQRT - Control single-precision floating-point square root (-prec-sqrt) support (1: true, default).
  • 1 : Enables the IEEE round-to-nearest mode
  • 0 : Enables the fast approximation mode

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_FMA - Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_NUM_OPTIONS - Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

See Also:

• Constant Field Values

CU_JIT_ERROR_LOG_BUFFER

public static final int CU_JIT_ERROR_LOG_BUFFER

Online compiler and linker options. (CUjit_option)

Enum values:

• JIT_MAX_REGISTERS - Max number of registers that a thread may use.

  Option type: unsigned int. Applies to: compiler only

• JIT_THREADS_PER_BLOCK - IN: Specifies minimum number of threads per block to target compilation for

  OUT: Returns the number of threads the compiler actually targeted.

  This restricts the resource utilization fo the compiler (e.g. max registers) such that a block with the given number of threads should be able to launch based on register limitations. Note, this option does not currently take into account any other resource limitations, such as shared memory utilization.

  Cannot be combined with JIT_TARGET. Option type: unsigned int. Applies to: compiler only

• JIT_WALL_TIME - Overwrites the option value with the total wall clock time, in milliseconds, spent in the compiler and linker.

  Option type: float. Applies to: compiler and linker

• JIT_INFO_LOG_BUFFER - Pointer to a buffer in which to print any log messages that are informational in nature (the buffer size is specified via option JIT_INFO_LOG_BUFFER_SIZE_BYTES).

  Option type: char *. Applies to: compiler and linker

• JIT_INFO_LOG_BUFFER_SIZE_BYTES - IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).

  OUT: Amount of log buffer filled with messages.

  Option type: unsigned int. Applies to: compiler and linker

• JIT_ERROR_LOG_BUFFER - Pointer to a buffer in which to print any log messages that reflect errors (the buffer size is specified via option JIT_ERROR_LOG_BUFFER_SIZE_BYTES).

  Option type: char *. Applies to: compiler and linker

• JIT_ERROR_LOG_BUFFER_SIZE_BYTES - IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).

  OUT: Amount of log buffer filled with messages.

  Option type: unsigned int. Applies to: compiler and linker

• JIT_OPTIMIZATION_LEVEL - Level of optimizations to apply to generated code (0 - 4), with 4 being the default and highest level of optimizations.

  Option type: unsigned int. Applies to: compiler only

• JIT_TARGET_FROM_CUCONTEXT - No option value required. Determines the target based on the current attached context (default).

  Option type: No option value needed. Applies to: compiler and linker

• JIT_TARGET - Target is chosen based on supplied CUjit_target. Cannot be combined with JIT_THREADS_PER_BLOCK.

  Option type: unsigned int for enumerated type CUjit_target. Applies to: compiler and linker

• JIT_FALLBACK_STRATEGY - Specifies choice of fallback strategy if matching cubin is not found.

  Choice is based on supplied CUjit_fallback. This option cannot be used with cuLink* APIs as the linker requires exact matches.

  Option type: unsigned int for enumerated type CUjit_fallback. Applies to: compiler only

• JIT_GENERATE_DEBUG_INFO - Specifies whether to create debug information in output (-g) (0: false, default).

  Option type: int. Applies to: compiler and linker

• JIT_LOG_VERBOSE - Generate verbose log messages (0: false, default).

  Option type: int. Applies to: compiler and linker

• JIT_GENERATE_LINE_INFO - Generate line number information (-lineinfo) (0: false, default).

  Option type: int. Applies to: compiler only

• JIT_CACHE_MODE - Specifies whether to enable caching explicitly (-dlcm). Choice is based on supplied CUjit_cacheMode_enum.

  Option type: unsigned int for enumerated type CUjit_cacheMode_enum. Applies to: compiler only

• JIT_NEW_SM3X_OPT - Used for internal purposes only, in this version of CUDA.
• JIT_FAST_COMPILE - Used for internal purposes only, in this version of CUDA.
• JIT_GLOBAL_SYMBOL_NAMES - Array of device symbol names that will be relocated to the corresponing host addresses stored in JIT_GLOBAL_SYMBOL_ADDRESSES.

  Must contain JIT_GLOBAL_SYMBOL_COUNT entries. When loding a device module, driver will relocate all encountered unresolved symbols to the host addresses. It is only allowed to register symbols that correspond to unresolved global variables. It is illegal to register the same device symbol at multiple addresses.

  Option type: const char **. Applies to: dynamic linker only

• JIT_GLOBAL_SYMBOL_ADDRESSES - Array of host addresses that will be used to relocate corresponding device symbols stored in JIT_GLOBAL_SYMBOL_NAMES.

  Must contain JIT_GLOBAL_SYMBOL_COUNT entries.

  Option type: void **. Applies to: dynamic linker only

• JIT_GLOBAL_SYMBOL_COUNT - Number of entries in JIT_GLOBAL_SYMBOL_NAMES and JIT_GLOBAL_SYMBOL_ADDRESSES arrays.

  Option type: unsigned int. Applies to: dynamic linker only

• JIT_LTO - Enable link-time optimization (-dlto) for device code (0: false, default)

  Option type: int. Applies to: compiler and linker

• JIT_FTZ - Control single-precision denormals (-ftz) support (0: false, default).
  • 1 : flushes denormal values to zero
  • 0 : preserves denormal values

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_PREC_DIV - Control single-precision floating-point division and reciprocals (-prec-div) support (1: true, default).
  • 1 : Enables the IEEE round-to-nearest mode
  • 0 : Enables the fast approximation mode

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_PREC_SQRT - Control single-precision floating-point square root (-prec-sqrt) support (1: true, default).
  • 1 : Enables the IEEE round-to-nearest mode
  • 0 : Enables the fast approximation mode

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_FMA - Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_NUM_OPTIONS - Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

See Also:

• Constant Field Values

CU_JIT_ERROR_LOG_BUFFER_SIZE_BYTES

public static final int CU_JIT_ERROR_LOG_BUFFER_SIZE_BYTES

Online compiler and linker options. (CUjit_option)

Enum values:

• JIT_MAX_REGISTERS - Max number of registers that a thread may use.

  Option type: unsigned int. Applies to: compiler only

• JIT_THREADS_PER_BLOCK - IN: Specifies minimum number of threads per block to target compilation for

  OUT: Returns the number of threads the compiler actually targeted.

  This restricts the resource utilization fo the compiler (e.g. max registers) such that a block with the given number of threads should be able to launch based on register limitations. Note, this option does not currently take into account any other resource limitations, such as shared memory utilization.

  Cannot be combined with JIT_TARGET. Option type: unsigned int. Applies to: compiler only

• JIT_WALL_TIME - Overwrites the option value with the total wall clock time, in milliseconds, spent in the compiler and linker.

  Option type: float. Applies to: compiler and linker

• JIT_INFO_LOG_BUFFER - Pointer to a buffer in which to print any log messages that are informational in nature (the buffer size is specified via option JIT_INFO_LOG_BUFFER_SIZE_BYTES).

  Option type: char *. Applies to: compiler and linker

• JIT_INFO_LOG_BUFFER_SIZE_BYTES - IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).

  OUT: Amount of log buffer filled with messages.

  Option type: unsigned int. Applies to: compiler and linker

• JIT_ERROR_LOG_BUFFER - Pointer to a buffer in which to print any log messages that reflect errors (the buffer size is specified via option JIT_ERROR_LOG_BUFFER_SIZE_BYTES).

  Option type: char *. Applies to: compiler and linker

• JIT_ERROR_LOG_BUFFER_SIZE_BYTES - IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).

  OUT: Amount of log buffer filled with messages.

  Option type: unsigned int. Applies to: compiler and linker

• JIT_OPTIMIZATION_LEVEL - Level of optimizations to apply to generated code (0 - 4), with 4 being the default and highest level of optimizations.

  Option type: unsigned int. Applies to: compiler only

• JIT_TARGET_FROM_CUCONTEXT - No option value required. Determines the target based on the current attached context (default).

  Option type: No option value needed. Applies to: compiler and linker

• JIT_TARGET - Target is chosen based on supplied CUjit_target. Cannot be combined with JIT_THREADS_PER_BLOCK.

  Option type: unsigned int for enumerated type CUjit_target. Applies to: compiler and linker

• JIT_FALLBACK_STRATEGY - Specifies choice of fallback strategy if matching cubin is not found.

  Choice is based on supplied CUjit_fallback. This option cannot be used with cuLink* APIs as the linker requires exact matches.

  Option type: unsigned int for enumerated type CUjit_fallback. Applies to: compiler only

• JIT_GENERATE_DEBUG_INFO - Specifies whether to create debug information in output (-g) (0: false, default).

  Option type: int. Applies to: compiler and linker

• JIT_LOG_VERBOSE - Generate verbose log messages (0: false, default).

  Option type: int. Applies to: compiler and linker

• JIT_GENERATE_LINE_INFO - Generate line number information (-lineinfo) (0: false, default).

  Option type: int. Applies to: compiler only

• JIT_CACHE_MODE - Specifies whether to enable caching explicitly (-dlcm). Choice is based on supplied CUjit_cacheMode_enum.

  Option type: unsigned int for enumerated type CUjit_cacheMode_enum. Applies to: compiler only

• JIT_NEW_SM3X_OPT - Used for internal purposes only, in this version of CUDA.
• JIT_FAST_COMPILE - Used for internal purposes only, in this version of CUDA.
• JIT_GLOBAL_SYMBOL_NAMES - Array of device symbol names that will be relocated to the corresponing host addresses stored in JIT_GLOBAL_SYMBOL_ADDRESSES.

  Must contain JIT_GLOBAL_SYMBOL_COUNT entries. When loding a device module, driver will relocate all encountered unresolved symbols to the host addresses. It is only allowed to register symbols that correspond to unresolved global variables. It is illegal to register the same device symbol at multiple addresses.

  Option type: const char **. Applies to: dynamic linker only

• JIT_GLOBAL_SYMBOL_ADDRESSES - Array of host addresses that will be used to relocate corresponding device symbols stored in JIT_GLOBAL_SYMBOL_NAMES.

  Must contain JIT_GLOBAL_SYMBOL_COUNT entries.

  Option type: void **. Applies to: dynamic linker only

• JIT_GLOBAL_SYMBOL_COUNT - Number of entries in JIT_GLOBAL_SYMBOL_NAMES and JIT_GLOBAL_SYMBOL_ADDRESSES arrays.

  Option type: unsigned int. Applies to: dynamic linker only

• JIT_LTO - Enable link-time optimization (-dlto) for device code (0: false, default)

  Option type: int. Applies to: compiler and linker

• JIT_FTZ - Control single-precision denormals (-ftz) support (0: false, default).
  • 1 : flushes denormal values to zero
  • 0 : preserves denormal values

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_PREC_DIV - Control single-precision floating-point division and reciprocals (-prec-div) support (1: true, default).
  • 1 : Enables the IEEE round-to-nearest mode
  • 0 : Enables the fast approximation mode

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_PREC_SQRT - Control single-precision floating-point square root (-prec-sqrt) support (1: true, default).
  • 1 : Enables the IEEE round-to-nearest mode
  • 0 : Enables the fast approximation mode

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_FMA - Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_NUM_OPTIONS - Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

See Also:

• Constant Field Values

CU_JIT_OPTIMIZATION_LEVEL

public static final int CU_JIT_OPTIMIZATION_LEVEL

Online compiler and linker options. (CUjit_option)

Enum values:

• JIT_MAX_REGISTERS - Max number of registers that a thread may use.

  Option type: unsigned int. Applies to: compiler only

• JIT_THREADS_PER_BLOCK - IN: Specifies minimum number of threads per block to target compilation for

  OUT: Returns the number of threads the compiler actually targeted.

  This restricts the resource utilization fo the compiler (e.g. max registers) such that a block with the given number of threads should be able to launch based on register limitations. Note, this option does not currently take into account any other resource limitations, such as shared memory utilization.

  Cannot be combined with JIT_TARGET. Option type: unsigned int. Applies to: compiler only

• JIT_WALL_TIME - Overwrites the option value with the total wall clock time, in milliseconds, spent in the compiler and linker.

  Option type: float. Applies to: compiler and linker

• JIT_INFO_LOG_BUFFER - Pointer to a buffer in which to print any log messages that are informational in nature (the buffer size is specified via option JIT_INFO_LOG_BUFFER_SIZE_BYTES).

  Option type: char *. Applies to: compiler and linker

• JIT_INFO_LOG_BUFFER_SIZE_BYTES - IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).

  OUT: Amount of log buffer filled with messages.

  Option type: unsigned int. Applies to: compiler and linker

• JIT_ERROR_LOG_BUFFER - Pointer to a buffer in which to print any log messages that reflect errors (the buffer size is specified via option JIT_ERROR_LOG_BUFFER_SIZE_BYTES).

  Option type: char *. Applies to: compiler and linker

• JIT_ERROR_LOG_BUFFER_SIZE_BYTES - IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).

  OUT: Amount of log buffer filled with messages.

  Option type: unsigned int. Applies to: compiler and linker

• JIT_OPTIMIZATION_LEVEL - Level of optimizations to apply to generated code (0 - 4), with 4 being the default and highest level of optimizations.

  Option type: unsigned int. Applies to: compiler only

• JIT_TARGET_FROM_CUCONTEXT - No option value required. Determines the target based on the current attached context (default).

  Option type: No option value needed. Applies to: compiler and linker

• JIT_TARGET - Target is chosen based on supplied CUjit_target. Cannot be combined with JIT_THREADS_PER_BLOCK.

  Option type: unsigned int for enumerated type CUjit_target. Applies to: compiler and linker

• JIT_FALLBACK_STRATEGY - Specifies choice of fallback strategy if matching cubin is not found.

  Choice is based on supplied CUjit_fallback. This option cannot be used with cuLink* APIs as the linker requires exact matches.

  Option type: unsigned int for enumerated type CUjit_fallback. Applies to: compiler only

• JIT_GENERATE_DEBUG_INFO - Specifies whether to create debug information in output (-g) (0: false, default).

  Option type: int. Applies to: compiler and linker

• JIT_LOG_VERBOSE - Generate verbose log messages (0: false, default).

  Option type: int. Applies to: compiler and linker

• JIT_GENERATE_LINE_INFO - Generate line number information (-lineinfo) (0: false, default).

  Option type: int. Applies to: compiler only

• JIT_CACHE_MODE - Specifies whether to enable caching explicitly (-dlcm). Choice is based on supplied CUjit_cacheMode_enum.

  Option type: unsigned int for enumerated type CUjit_cacheMode_enum. Applies to: compiler only

• JIT_NEW_SM3X_OPT - Used for internal purposes only, in this version of CUDA.
• JIT_FAST_COMPILE - Used for internal purposes only, in this version of CUDA.
• JIT_GLOBAL_SYMBOL_NAMES - Array of device symbol names that will be relocated to the corresponing host addresses stored in JIT_GLOBAL_SYMBOL_ADDRESSES.

  Must contain JIT_GLOBAL_SYMBOL_COUNT entries. When loding a device module, driver will relocate all encountered unresolved symbols to the host addresses. It is only allowed to register symbols that correspond to unresolved global variables. It is illegal to register the same device symbol at multiple addresses.

  Option type: const char **. Applies to: dynamic linker only

• JIT_GLOBAL_SYMBOL_ADDRESSES - Array of host addresses that will be used to relocate corresponding device symbols stored in JIT_GLOBAL_SYMBOL_NAMES.

  Must contain JIT_GLOBAL_SYMBOL_COUNT entries.

  Option type: void **. Applies to: dynamic linker only

• JIT_GLOBAL_SYMBOL_COUNT - Number of entries in JIT_GLOBAL_SYMBOL_NAMES and JIT_GLOBAL_SYMBOL_ADDRESSES arrays.

  Option type: unsigned int. Applies to: dynamic linker only

• JIT_LTO - Enable link-time optimization (-dlto) for device code (0: false, default)

  Option type: int. Applies to: compiler and linker

• JIT_FTZ - Control single-precision denormals (-ftz) support (0: false, default).
  • 1 : flushes denormal values to zero
  • 0 : preserves denormal values

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_PREC_DIV - Control single-precision floating-point division and reciprocals (-prec-div) support (1: true, default).
  • 1 : Enables the IEEE round-to-nearest mode
  • 0 : Enables the fast approximation mode

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_PREC_SQRT - Control single-precision floating-point square root (-prec-sqrt) support (1: true, default).
  • 1 : Enables the IEEE round-to-nearest mode
  • 0 : Enables the fast approximation mode

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_FMA - Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_NUM_OPTIONS - Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

See Also:

• Constant Field Values

CU_JIT_TARGET_FROM_CUCONTEXT

public static final int CU_JIT_TARGET_FROM_CUCONTEXT

Online compiler and linker options. (CUjit_option)

Enum values:

• JIT_MAX_REGISTERS - Max number of registers that a thread may use.

  Option type: unsigned int. Applies to: compiler only

• JIT_THREADS_PER_BLOCK - IN: Specifies minimum number of threads per block to target compilation for

  OUT: Returns the number of threads the compiler actually targeted.

  This restricts the resource utilization fo the compiler (e.g. max registers) such that a block with the given number of threads should be able to launch based on register limitations. Note, this option does not currently take into account any other resource limitations, such as shared memory utilization.

  Cannot be combined with JIT_TARGET. Option type: unsigned int. Applies to: compiler only

• JIT_WALL_TIME - Overwrites the option value with the total wall clock time, in milliseconds, spent in the compiler and linker.

  Option type: float. Applies to: compiler and linker

• JIT_INFO_LOG_BUFFER - Pointer to a buffer in which to print any log messages that are informational in nature (the buffer size is specified via option JIT_INFO_LOG_BUFFER_SIZE_BYTES).

  Option type: char *. Applies to: compiler and linker

• JIT_INFO_LOG_BUFFER_SIZE_BYTES - IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).

  OUT: Amount of log buffer filled with messages.

  Option type: unsigned int. Applies to: compiler and linker

• JIT_ERROR_LOG_BUFFER - Pointer to a buffer in which to print any log messages that reflect errors (the buffer size is specified via option JIT_ERROR_LOG_BUFFER_SIZE_BYTES).

  Option type: char *. Applies to: compiler and linker

• JIT_ERROR_LOG_BUFFER_SIZE_BYTES - IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).

  OUT: Amount of log buffer filled with messages.

  Option type: unsigned int. Applies to: compiler and linker

• JIT_OPTIMIZATION_LEVEL - Level of optimizations to apply to generated code (0 - 4), with 4 being the default and highest level of optimizations.

  Option type: unsigned int. Applies to: compiler only

• JIT_TARGET_FROM_CUCONTEXT - No option value required. Determines the target based on the current attached context (default).

  Option type: No option value needed. Applies to: compiler and linker

• JIT_TARGET - Target is chosen based on supplied CUjit_target. Cannot be combined with JIT_THREADS_PER_BLOCK.

  Option type: unsigned int for enumerated type CUjit_target. Applies to: compiler and linker

• JIT_FALLBACK_STRATEGY - Specifies choice of fallback strategy if matching cubin is not found.

  Choice is based on supplied CUjit_fallback. This option cannot be used with cuLink* APIs as the linker requires exact matches.

  Option type: unsigned int for enumerated type CUjit_fallback. Applies to: compiler only

• JIT_GENERATE_DEBUG_INFO - Specifies whether to create debug information in output (-g) (0: false, default).

  Option type: int. Applies to: compiler and linker

• JIT_LOG_VERBOSE - Generate verbose log messages (0: false, default).

  Option type: int. Applies to: compiler and linker

• JIT_GENERATE_LINE_INFO - Generate line number information (-lineinfo) (0: false, default).

  Option type: int. Applies to: compiler only

• JIT_CACHE_MODE - Specifies whether to enable caching explicitly (-dlcm). Choice is based on supplied CUjit_cacheMode_enum.

  Option type: unsigned int for enumerated type CUjit_cacheMode_enum. Applies to: compiler only

• JIT_NEW_SM3X_OPT - Used for internal purposes only, in this version of CUDA.
• JIT_FAST_COMPILE - Used for internal purposes only, in this version of CUDA.
• JIT_GLOBAL_SYMBOL_NAMES - Array of device symbol names that will be relocated to the corresponing host addresses stored in JIT_GLOBAL_SYMBOL_ADDRESSES.

  Must contain JIT_GLOBAL_SYMBOL_COUNT entries. When loding a device module, driver will relocate all encountered unresolved symbols to the host addresses. It is only allowed to register symbols that correspond to unresolved global variables. It is illegal to register the same device symbol at multiple addresses.

  Option type: const char **. Applies to: dynamic linker only

• JIT_GLOBAL_SYMBOL_ADDRESSES - Array of host addresses that will be used to relocate corresponding device symbols stored in JIT_GLOBAL_SYMBOL_NAMES.

  Must contain JIT_GLOBAL_SYMBOL_COUNT entries.

  Option type: void **. Applies to: dynamic linker only

• JIT_GLOBAL_SYMBOL_COUNT - Number of entries in JIT_GLOBAL_SYMBOL_NAMES and JIT_GLOBAL_SYMBOL_ADDRESSES arrays.

  Option type: unsigned int. Applies to: dynamic linker only

• JIT_LTO - Enable link-time optimization (-dlto) for device code (0: false, default)

  Option type: int. Applies to: compiler and linker

• JIT_FTZ - Control single-precision denormals (-ftz) support (0: false, default).
  • 1 : flushes denormal values to zero
  • 0 : preserves denormal values

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_PREC_DIV - Control single-precision floating-point division and reciprocals (-prec-div) support (1: true, default).
  • 1 : Enables the IEEE round-to-nearest mode
  • 0 : Enables the fast approximation mode

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_PREC_SQRT - Control single-precision floating-point square root (-prec-sqrt) support (1: true, default).
  • 1 : Enables the IEEE round-to-nearest mode
  • 0 : Enables the fast approximation mode

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_FMA - Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_NUM_OPTIONS - Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

See Also:

• Constant Field Values

CU_JIT_TARGET

public static final int CU_JIT_TARGET

Online compiler and linker options. (CUjit_option)

Enum values:

• JIT_MAX_REGISTERS - Max number of registers that a thread may use.

  Option type: unsigned int. Applies to: compiler only

• JIT_THREADS_PER_BLOCK - IN: Specifies minimum number of threads per block to target compilation for

  OUT: Returns the number of threads the compiler actually targeted.

  This restricts the resource utilization fo the compiler (e.g. max registers) such that a block with the given number of threads should be able to launch based on register limitations. Note, this option does not currently take into account any other resource limitations, such as shared memory utilization.

  Cannot be combined with JIT_TARGET. Option type: unsigned int. Applies to: compiler only

• JIT_WALL_TIME - Overwrites the option value with the total wall clock time, in milliseconds, spent in the compiler and linker.

  Option type: float. Applies to: compiler and linker

• JIT_INFO_LOG_BUFFER - Pointer to a buffer in which to print any log messages that are informational in nature (the buffer size is specified via option JIT_INFO_LOG_BUFFER_SIZE_BYTES).

  Option type: char *. Applies to: compiler and linker

• JIT_INFO_LOG_BUFFER_SIZE_BYTES - IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).

  OUT: Amount of log buffer filled with messages.

  Option type: unsigned int. Applies to: compiler and linker

• JIT_ERROR_LOG_BUFFER - Pointer to a buffer in which to print any log messages that reflect errors (the buffer size is specified via option JIT_ERROR_LOG_BUFFER_SIZE_BYTES).

  Option type: char *. Applies to: compiler and linker

• JIT_ERROR_LOG_BUFFER_SIZE_BYTES - IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).

  OUT: Amount of log buffer filled with messages.

  Option type: unsigned int. Applies to: compiler and linker

• JIT_OPTIMIZATION_LEVEL - Level of optimizations to apply to generated code (0 - 4), with 4 being the default and highest level of optimizations.

  Option type: unsigned int. Applies to: compiler only

• JIT_TARGET_FROM_CUCONTEXT - No option value required. Determines the target based on the current attached context (default).

  Option type: No option value needed. Applies to: compiler and linker

• JIT_TARGET - Target is chosen based on supplied CUjit_target. Cannot be combined with JIT_THREADS_PER_BLOCK.

  Option type: unsigned int for enumerated type CUjit_target. Applies to: compiler and linker

• JIT_FALLBACK_STRATEGY - Specifies choice of fallback strategy if matching cubin is not found.

  Choice is based on supplied CUjit_fallback. This option cannot be used with cuLink* APIs as the linker requires exact matches.

  Option type: unsigned int for enumerated type CUjit_fallback. Applies to: compiler only

• JIT_GENERATE_DEBUG_INFO - Specifies whether to create debug information in output (-g) (0: false, default).

  Option type: int. Applies to: compiler and linker

• JIT_LOG_VERBOSE - Generate verbose log messages (0: false, default).

  Option type: int. Applies to: compiler and linker

• JIT_GENERATE_LINE_INFO - Generate line number information (-lineinfo) (0: false, default).

  Option type: int. Applies to: compiler only

• JIT_CACHE_MODE - Specifies whether to enable caching explicitly (-dlcm). Choice is based on supplied CUjit_cacheMode_enum.

  Option type: unsigned int for enumerated type CUjit_cacheMode_enum. Applies to: compiler only

• JIT_NEW_SM3X_OPT - Used for internal purposes only, in this version of CUDA.
• JIT_FAST_COMPILE - Used for internal purposes only, in this version of CUDA.
• JIT_GLOBAL_SYMBOL_NAMES - Array of device symbol names that will be relocated to the corresponing host addresses stored in JIT_GLOBAL_SYMBOL_ADDRESSES.

  Must contain JIT_GLOBAL_SYMBOL_COUNT entries. When loding a device module, driver will relocate all encountered unresolved symbols to the host addresses. It is only allowed to register symbols that correspond to unresolved global variables. It is illegal to register the same device symbol at multiple addresses.

  Option type: const char **. Applies to: dynamic linker only

• JIT_GLOBAL_SYMBOL_ADDRESSES - Array of host addresses that will be used to relocate corresponding device symbols stored in JIT_GLOBAL_SYMBOL_NAMES.

  Must contain JIT_GLOBAL_SYMBOL_COUNT entries.

  Option type: void **. Applies to: dynamic linker only

• JIT_GLOBAL_SYMBOL_COUNT - Number of entries in JIT_GLOBAL_SYMBOL_NAMES and JIT_GLOBAL_SYMBOL_ADDRESSES arrays.

  Option type: unsigned int. Applies to: dynamic linker only

• JIT_LTO - Enable link-time optimization (-dlto) for device code (0: false, default)

  Option type: int. Applies to: compiler and linker

• JIT_FTZ - Control single-precision denormals (-ftz) support (0: false, default).
  • 1 : flushes denormal values to zero
  • 0 : preserves denormal values

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_PREC_DIV - Control single-precision floating-point division and reciprocals (-prec-div) support (1: true, default).
  • 1 : Enables the IEEE round-to-nearest mode
  • 0 : Enables the fast approximation mode

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_PREC_SQRT - Control single-precision floating-point square root (-prec-sqrt) support (1: true, default).
  • 1 : Enables the IEEE round-to-nearest mode
  • 0 : Enables the fast approximation mode

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_FMA - Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_NUM_OPTIONS - Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

See Also:

• Constant Field Values

CU_JIT_FALLBACK_STRATEGY

public static final int CU_JIT_FALLBACK_STRATEGY

Online compiler and linker options. (CUjit_option)

Enum values:

• JIT_MAX_REGISTERS - Max number of registers that a thread may use.

  Option type: unsigned int. Applies to: compiler only

• JIT_THREADS_PER_BLOCK - IN: Specifies minimum number of threads per block to target compilation for

  OUT: Returns the number of threads the compiler actually targeted.

  This restricts the resource utilization fo the compiler (e.g. max registers) such that a block with the given number of threads should be able to launch based on register limitations. Note, this option does not currently take into account any other resource limitations, such as shared memory utilization.

  Cannot be combined with JIT_TARGET. Option type: unsigned int. Applies to: compiler only

• JIT_WALL_TIME - Overwrites the option value with the total wall clock time, in milliseconds, spent in the compiler and linker.

  Option type: float. Applies to: compiler and linker

• JIT_INFO_LOG_BUFFER - Pointer to a buffer in which to print any log messages that are informational in nature (the buffer size is specified via option JIT_INFO_LOG_BUFFER_SIZE_BYTES).

  Option type: char *. Applies to: compiler and linker

• JIT_INFO_LOG_BUFFER_SIZE_BYTES - IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).

  OUT: Amount of log buffer filled with messages.

  Option type: unsigned int. Applies to: compiler and linker

• JIT_ERROR_LOG_BUFFER - Pointer to a buffer in which to print any log messages that reflect errors (the buffer size is specified via option JIT_ERROR_LOG_BUFFER_SIZE_BYTES).

  Option type: char *. Applies to: compiler and linker

• JIT_ERROR_LOG_BUFFER_SIZE_BYTES - IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).

  OUT: Amount of log buffer filled with messages.

  Option type: unsigned int. Applies to: compiler and linker

• JIT_OPTIMIZATION_LEVEL - Level of optimizations to apply to generated code (0 - 4), with 4 being the default and highest level of optimizations.

  Option type: unsigned int. Applies to: compiler only

• JIT_TARGET_FROM_CUCONTEXT - No option value required. Determines the target based on the current attached context (default).

  Option type: No option value needed. Applies to: compiler and linker

• JIT_TARGET - Target is chosen based on supplied CUjit_target. Cannot be combined with JIT_THREADS_PER_BLOCK.

  Option type: unsigned int for enumerated type CUjit_target. Applies to: compiler and linker

• JIT_FALLBACK_STRATEGY - Specifies choice of fallback strategy if matching cubin is not found.

  Choice is based on supplied CUjit_fallback. This option cannot be used with cuLink* APIs as the linker requires exact matches.

  Option type: unsigned int for enumerated type CUjit_fallback. Applies to: compiler only

• JIT_GENERATE_DEBUG_INFO - Specifies whether to create debug information in output (-g) (0: false, default).

  Option type: int. Applies to: compiler and linker

• JIT_LOG_VERBOSE - Generate verbose log messages (0: false, default).

  Option type: int. Applies to: compiler and linker

• JIT_GENERATE_LINE_INFO - Generate line number information (-lineinfo) (0: false, default).

  Option type: int. Applies to: compiler only

• JIT_CACHE_MODE - Specifies whether to enable caching explicitly (-dlcm). Choice is based on supplied CUjit_cacheMode_enum.

  Option type: unsigned int for enumerated type CUjit_cacheMode_enum. Applies to: compiler only

• JIT_NEW_SM3X_OPT - Used for internal purposes only, in this version of CUDA.
• JIT_FAST_COMPILE - Used for internal purposes only, in this version of CUDA.
• JIT_GLOBAL_SYMBOL_NAMES - Array of device symbol names that will be relocated to the corresponing host addresses stored in JIT_GLOBAL_SYMBOL_ADDRESSES.

  Must contain JIT_GLOBAL_SYMBOL_COUNT entries. When loding a device module, driver will relocate all encountered unresolved symbols to the host addresses. It is only allowed to register symbols that correspond to unresolved global variables. It is illegal to register the same device symbol at multiple addresses.

  Option type: const char **. Applies to: dynamic linker only

• JIT_GLOBAL_SYMBOL_ADDRESSES - Array of host addresses that will be used to relocate corresponding device symbols stored in JIT_GLOBAL_SYMBOL_NAMES.

  Must contain JIT_GLOBAL_SYMBOL_COUNT entries.

  Option type: void **. Applies to: dynamic linker only

• JIT_GLOBAL_SYMBOL_COUNT - Number of entries in JIT_GLOBAL_SYMBOL_NAMES and JIT_GLOBAL_SYMBOL_ADDRESSES arrays.

  Option type: unsigned int. Applies to: dynamic linker only

• JIT_LTO - Enable link-time optimization (-dlto) for device code (0: false, default)

  Option type: int. Applies to: compiler and linker

• JIT_FTZ - Control single-precision denormals (-ftz) support (0: false, default).
  • 1 : flushes denormal values to zero
  • 0 : preserves denormal values

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_PREC_DIV - Control single-precision floating-point division and reciprocals (-prec-div) support (1: true, default).
  • 1 : Enables the IEEE round-to-nearest mode
  • 0 : Enables the fast approximation mode

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_PREC_SQRT - Control single-precision floating-point square root (-prec-sqrt) support (1: true, default).
  • 1 : Enables the IEEE round-to-nearest mode
  • 0 : Enables the fast approximation mode

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_FMA - Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_NUM_OPTIONS - Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

See Also:

• Constant Field Values

CU_JIT_GENERATE_DEBUG_INFO

public static final int CU_JIT_GENERATE_DEBUG_INFO

Online compiler and linker options. (CUjit_option)

Enum values:

• JIT_MAX_REGISTERS - Max number of registers that a thread may use.

  Option type: unsigned int. Applies to: compiler only

• JIT_THREADS_PER_BLOCK - IN: Specifies minimum number of threads per block to target compilation for

  OUT: Returns the number of threads the compiler actually targeted.

  This restricts the resource utilization fo the compiler (e.g. max registers) such that a block with the given number of threads should be able to launch based on register limitations. Note, this option does not currently take into account any other resource limitations, such as shared memory utilization.

  Cannot be combined with JIT_TARGET. Option type: unsigned int. Applies to: compiler only

• JIT_WALL_TIME - Overwrites the option value with the total wall clock time, in milliseconds, spent in the compiler and linker.

  Option type: float. Applies to: compiler and linker

• JIT_INFO_LOG_BUFFER - Pointer to a buffer in which to print any log messages that are informational in nature (the buffer size is specified via option JIT_INFO_LOG_BUFFER_SIZE_BYTES).

  Option type: char *. Applies to: compiler and linker

• JIT_INFO_LOG_BUFFER_SIZE_BYTES - IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).

  OUT: Amount of log buffer filled with messages.

  Option type: unsigned int. Applies to: compiler and linker

• JIT_ERROR_LOG_BUFFER - Pointer to a buffer in which to print any log messages that reflect errors (the buffer size is specified via option JIT_ERROR_LOG_BUFFER_SIZE_BYTES).

  Option type: char *. Applies to: compiler and linker

• JIT_ERROR_LOG_BUFFER_SIZE_BYTES - IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).

  OUT: Amount of log buffer filled with messages.

  Option type: unsigned int. Applies to: compiler and linker

• JIT_OPTIMIZATION_LEVEL - Level of optimizations to apply to generated code (0 - 4), with 4 being the default and highest level of optimizations.

  Option type: unsigned int. Applies to: compiler only

• JIT_TARGET_FROM_CUCONTEXT - No option value required. Determines the target based on the current attached context (default).

  Option type: No option value needed. Applies to: compiler and linker

• JIT_TARGET - Target is chosen based on supplied CUjit_target. Cannot be combined with JIT_THREADS_PER_BLOCK.

  Option type: unsigned int for enumerated type CUjit_target. Applies to: compiler and linker

• JIT_FALLBACK_STRATEGY - Specifies choice of fallback strategy if matching cubin is not found.

  Choice is based on supplied CUjit_fallback. This option cannot be used with cuLink* APIs as the linker requires exact matches.

  Option type: unsigned int for enumerated type CUjit_fallback. Applies to: compiler only

• JIT_GENERATE_DEBUG_INFO - Specifies whether to create debug information in output (-g) (0: false, default).

  Option type: int. Applies to: compiler and linker

• JIT_LOG_VERBOSE - Generate verbose log messages (0: false, default).

  Option type: int. Applies to: compiler and linker

• JIT_GENERATE_LINE_INFO - Generate line number information (-lineinfo) (0: false, default).

  Option type: int. Applies to: compiler only

• JIT_CACHE_MODE - Specifies whether to enable caching explicitly (-dlcm). Choice is based on supplied CUjit_cacheMode_enum.

  Option type: unsigned int for enumerated type CUjit_cacheMode_enum. Applies to: compiler only

• JIT_NEW_SM3X_OPT - Used for internal purposes only, in this version of CUDA.
• JIT_FAST_COMPILE - Used for internal purposes only, in this version of CUDA.
• JIT_GLOBAL_SYMBOL_NAMES - Array of device symbol names that will be relocated to the corresponing host addresses stored in JIT_GLOBAL_SYMBOL_ADDRESSES.

  Must contain JIT_GLOBAL_SYMBOL_COUNT entries. When loding a device module, driver will relocate all encountered unresolved symbols to the host addresses. It is only allowed to register symbols that correspond to unresolved global variables. It is illegal to register the same device symbol at multiple addresses.

  Option type: const char **. Applies to: dynamic linker only

• JIT_GLOBAL_SYMBOL_ADDRESSES - Array of host addresses that will be used to relocate corresponding device symbols stored in JIT_GLOBAL_SYMBOL_NAMES.

  Must contain JIT_GLOBAL_SYMBOL_COUNT entries.

  Option type: void **. Applies to: dynamic linker only

• JIT_GLOBAL_SYMBOL_COUNT - Number of entries in JIT_GLOBAL_SYMBOL_NAMES and JIT_GLOBAL_SYMBOL_ADDRESSES arrays.

  Option type: unsigned int. Applies to: dynamic linker only

• JIT_LTO - Enable link-time optimization (-dlto) for device code (0: false, default)

  Option type: int. Applies to: compiler and linker

• JIT_FTZ - Control single-precision denormals (-ftz) support (0: false, default).
  • 1 : flushes denormal values to zero
  • 0 : preserves denormal values

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_PREC_DIV - Control single-precision floating-point division and reciprocals (-prec-div) support (1: true, default).
  • 1 : Enables the IEEE round-to-nearest mode
  • 0 : Enables the fast approximation mode

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_PREC_SQRT - Control single-precision floating-point square root (-prec-sqrt) support (1: true, default).
  • 1 : Enables the IEEE round-to-nearest mode
  • 0 : Enables the fast approximation mode

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_FMA - Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_NUM_OPTIONS - Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

See Also:

• Constant Field Values

CU_JIT_LOG_VERBOSE

public static final int CU_JIT_LOG_VERBOSE

Online compiler and linker options. (CUjit_option)

Enum values:

• JIT_MAX_REGISTERS - Max number of registers that a thread may use.

  Option type: unsigned int. Applies to: compiler only

• JIT_THREADS_PER_BLOCK - IN: Specifies minimum number of threads per block to target compilation for

  OUT: Returns the number of threads the compiler actually targeted.

  This restricts the resource utilization fo the compiler (e.g. max registers) such that a block with the given number of threads should be able to launch based on register limitations. Note, this option does not currently take into account any other resource limitations, such as shared memory utilization.

  Cannot be combined with JIT_TARGET. Option type: unsigned int. Applies to: compiler only

• JIT_WALL_TIME - Overwrites the option value with the total wall clock time, in milliseconds, spent in the compiler and linker.

  Option type: float. Applies to: compiler and linker

• JIT_INFO_LOG_BUFFER - Pointer to a buffer in which to print any log messages that are informational in nature (the buffer size is specified via option JIT_INFO_LOG_BUFFER_SIZE_BYTES).

  Option type: char *. Applies to: compiler and linker

• JIT_INFO_LOG_BUFFER_SIZE_BYTES - IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).

  OUT: Amount of log buffer filled with messages.

  Option type: unsigned int. Applies to: compiler and linker

• JIT_ERROR_LOG_BUFFER - Pointer to a buffer in which to print any log messages that reflect errors (the buffer size is specified via option JIT_ERROR_LOG_BUFFER_SIZE_BYTES).

  Option type: char *. Applies to: compiler and linker

• JIT_ERROR_LOG_BUFFER_SIZE_BYTES - IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).

  OUT: Amount of log buffer filled with messages.

  Option type: unsigned int. Applies to: compiler and linker

• JIT_OPTIMIZATION_LEVEL - Level of optimizations to apply to generated code (0 - 4), with 4 being the default and highest level of optimizations.

  Option type: unsigned int. Applies to: compiler only

• JIT_TARGET_FROM_CUCONTEXT - No option value required. Determines the target based on the current attached context (default).

  Option type: No option value needed. Applies to: compiler and linker

• JIT_TARGET - Target is chosen based on supplied CUjit_target. Cannot be combined with JIT_THREADS_PER_BLOCK.

  Option type: unsigned int for enumerated type CUjit_target. Applies to: compiler and linker

• JIT_FALLBACK_STRATEGY - Specifies choice of fallback strategy if matching cubin is not found.

  Choice is based on supplied CUjit_fallback. This option cannot be used with cuLink* APIs as the linker requires exact matches.

  Option type: unsigned int for enumerated type CUjit_fallback. Applies to: compiler only

• JIT_GENERATE_DEBUG_INFO - Specifies whether to create debug information in output (-g) (0: false, default).

  Option type: int. Applies to: compiler and linker

• JIT_LOG_VERBOSE - Generate verbose log messages (0: false, default).

  Option type: int. Applies to: compiler and linker

• JIT_GENERATE_LINE_INFO - Generate line number information (-lineinfo) (0: false, default).

  Option type: int. Applies to: compiler only

• JIT_CACHE_MODE - Specifies whether to enable caching explicitly (-dlcm). Choice is based on supplied CUjit_cacheMode_enum.

  Option type: unsigned int for enumerated type CUjit_cacheMode_enum. Applies to: compiler only

• JIT_NEW_SM3X_OPT - Used for internal purposes only, in this version of CUDA.
• JIT_FAST_COMPILE - Used for internal purposes only, in this version of CUDA.
• JIT_GLOBAL_SYMBOL_NAMES - Array of device symbol names that will be relocated to the corresponing host addresses stored in JIT_GLOBAL_SYMBOL_ADDRESSES.

  Must contain JIT_GLOBAL_SYMBOL_COUNT entries. When loding a device module, driver will relocate all encountered unresolved symbols to the host addresses. It is only allowed to register symbols that correspond to unresolved global variables. It is illegal to register the same device symbol at multiple addresses.

  Option type: const char **. Applies to: dynamic linker only

• JIT_GLOBAL_SYMBOL_ADDRESSES - Array of host addresses that will be used to relocate corresponding device symbols stored in JIT_GLOBAL_SYMBOL_NAMES.

  Must contain JIT_GLOBAL_SYMBOL_COUNT entries.

  Option type: void **. Applies to: dynamic linker only

• JIT_GLOBAL_SYMBOL_COUNT - Number of entries in JIT_GLOBAL_SYMBOL_NAMES and JIT_GLOBAL_SYMBOL_ADDRESSES arrays.

  Option type: unsigned int. Applies to: dynamic linker only

• JIT_LTO - Enable link-time optimization (-dlto) for device code (0: false, default)

  Option type: int. Applies to: compiler and linker

• JIT_FTZ - Control single-precision denormals (-ftz) support (0: false, default).
  • 1 : flushes denormal values to zero
  • 0 : preserves denormal values

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_PREC_DIV - Control single-precision floating-point division and reciprocals (-prec-div) support (1: true, default).
  • 1 : Enables the IEEE round-to-nearest mode
  • 0 : Enables the fast approximation mode

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_PREC_SQRT - Control single-precision floating-point square root (-prec-sqrt) support (1: true, default).
  • 1 : Enables the IEEE round-to-nearest mode
  • 0 : Enables the fast approximation mode

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_FMA - Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_NUM_OPTIONS - Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

See Also:

• Constant Field Values

CU_JIT_GENERATE_LINE_INFO

public static final int CU_JIT_GENERATE_LINE_INFO

Online compiler and linker options. (CUjit_option)

Enum values:

• JIT_MAX_REGISTERS - Max number of registers that a thread may use.

  Option type: unsigned int. Applies to: compiler only

• JIT_THREADS_PER_BLOCK - IN: Specifies minimum number of threads per block to target compilation for

  OUT: Returns the number of threads the compiler actually targeted.

  This restricts the resource utilization fo the compiler (e.g. max registers) such that a block with the given number of threads should be able to launch based on register limitations. Note, this option does not currently take into account any other resource limitations, such as shared memory utilization.

  Cannot be combined with JIT_TARGET. Option type: unsigned int. Applies to: compiler only

• JIT_WALL_TIME - Overwrites the option value with the total wall clock time, in milliseconds, spent in the compiler and linker.

  Option type: float. Applies to: compiler and linker

• JIT_INFO_LOG_BUFFER - Pointer to a buffer in which to print any log messages that are informational in nature (the buffer size is specified via option JIT_INFO_LOG_BUFFER_SIZE_BYTES).

  Option type: char *. Applies to: compiler and linker

• JIT_INFO_LOG_BUFFER_SIZE_BYTES - IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).

  OUT: Amount of log buffer filled with messages.

  Option type: unsigned int. Applies to: compiler and linker

• JIT_ERROR_LOG_BUFFER - Pointer to a buffer in which to print any log messages that reflect errors (the buffer size is specified via option JIT_ERROR_LOG_BUFFER_SIZE_BYTES).

  Option type: char *. Applies to: compiler and linker

• JIT_ERROR_LOG_BUFFER_SIZE_BYTES - IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).

  OUT: Amount of log buffer filled with messages.

  Option type: unsigned int. Applies to: compiler and linker

• JIT_OPTIMIZATION_LEVEL - Level of optimizations to apply to generated code (0 - 4), with 4 being the default and highest level of optimizations.

  Option type: unsigned int. Applies to: compiler only

• JIT_TARGET_FROM_CUCONTEXT - No option value required. Determines the target based on the current attached context (default).

  Option type: No option value needed. Applies to: compiler and linker

• JIT_TARGET - Target is chosen based on supplied CUjit_target. Cannot be combined with JIT_THREADS_PER_BLOCK.

  Option type: unsigned int for enumerated type CUjit_target. Applies to: compiler and linker

• JIT_FALLBACK_STRATEGY - Specifies choice of fallback strategy if matching cubin is not found.

  Choice is based on supplied CUjit_fallback. This option cannot be used with cuLink* APIs as the linker requires exact matches.

  Option type: unsigned int for enumerated type CUjit_fallback. Applies to: compiler only

• JIT_GENERATE_DEBUG_INFO - Specifies whether to create debug information in output (-g) (0: false, default).

  Option type: int. Applies to: compiler and linker

• JIT_LOG_VERBOSE - Generate verbose log messages (0: false, default).

  Option type: int. Applies to: compiler and linker

• JIT_GENERATE_LINE_INFO - Generate line number information (-lineinfo) (0: false, default).

  Option type: int. Applies to: compiler only

• JIT_CACHE_MODE - Specifies whether to enable caching explicitly (-dlcm). Choice is based on supplied CUjit_cacheMode_enum.

  Option type: unsigned int for enumerated type CUjit_cacheMode_enum. Applies to: compiler only

• JIT_NEW_SM3X_OPT - Used for internal purposes only, in this version of CUDA.
• JIT_FAST_COMPILE - Used for internal purposes only, in this version of CUDA.
• JIT_GLOBAL_SYMBOL_NAMES - Array of device symbol names that will be relocated to the corresponing host addresses stored in JIT_GLOBAL_SYMBOL_ADDRESSES.

  Must contain JIT_GLOBAL_SYMBOL_COUNT entries. When loding a device module, driver will relocate all encountered unresolved symbols to the host addresses. It is only allowed to register symbols that correspond to unresolved global variables. It is illegal to register the same device symbol at multiple addresses.

  Option type: const char **. Applies to: dynamic linker only

• JIT_GLOBAL_SYMBOL_ADDRESSES - Array of host addresses that will be used to relocate corresponding device symbols stored in JIT_GLOBAL_SYMBOL_NAMES.

  Must contain JIT_GLOBAL_SYMBOL_COUNT entries.

  Option type: void **. Applies to: dynamic linker only

• JIT_GLOBAL_SYMBOL_COUNT - Number of entries in JIT_GLOBAL_SYMBOL_NAMES and JIT_GLOBAL_SYMBOL_ADDRESSES arrays.

  Option type: unsigned int. Applies to: dynamic linker only

• JIT_LTO - Enable link-time optimization (-dlto) for device code (0: false, default)

  Option type: int. Applies to: compiler and linker

• JIT_FTZ - Control single-precision denormals (-ftz) support (0: false, default).
  • 1 : flushes denormal values to zero
  • 0 : preserves denormal values

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_PREC_DIV - Control single-precision floating-point division and reciprocals (-prec-div) support (1: true, default).
  • 1 : Enables the IEEE round-to-nearest mode
  • 0 : Enables the fast approximation mode

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_PREC_SQRT - Control single-precision floating-point square root (-prec-sqrt) support (1: true, default).
  • 1 : Enables the IEEE round-to-nearest mode
  • 0 : Enables the fast approximation mode

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_FMA - Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_NUM_OPTIONS - Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

See Also:

• Constant Field Values

CU_JIT_CACHE_MODE

public static final int CU_JIT_CACHE_MODE

Online compiler and linker options. (CUjit_option)

Enum values:

• JIT_MAX_REGISTERS - Max number of registers that a thread may use.

  Option type: unsigned int. Applies to: compiler only

• JIT_THREADS_PER_BLOCK - IN: Specifies minimum number of threads per block to target compilation for

  OUT: Returns the number of threads the compiler actually targeted.

  This restricts the resource utilization fo the compiler (e.g. max registers) such that a block with the given number of threads should be able to launch based on register limitations. Note, this option does not currently take into account any other resource limitations, such as shared memory utilization.

  Cannot be combined with JIT_TARGET. Option type: unsigned int. Applies to: compiler only

• JIT_WALL_TIME - Overwrites the option value with the total wall clock time, in milliseconds, spent in the compiler and linker.

  Option type: float. Applies to: compiler and linker

• JIT_INFO_LOG_BUFFER - Pointer to a buffer in which to print any log messages that are informational in nature (the buffer size is specified via option JIT_INFO_LOG_BUFFER_SIZE_BYTES).

  Option type: char *. Applies to: compiler and linker

• JIT_INFO_LOG_BUFFER_SIZE_BYTES - IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).

  OUT: Amount of log buffer filled with messages.

  Option type: unsigned int. Applies to: compiler and linker

• JIT_ERROR_LOG_BUFFER - Pointer to a buffer in which to print any log messages that reflect errors (the buffer size is specified via option JIT_ERROR_LOG_BUFFER_SIZE_BYTES).

  Option type: char *. Applies to: compiler and linker

• JIT_ERROR_LOG_BUFFER_SIZE_BYTES - IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).

  OUT: Amount of log buffer filled with messages.

  Option type: unsigned int. Applies to: compiler and linker

• JIT_OPTIMIZATION_LEVEL - Level of optimizations to apply to generated code (0 - 4), with 4 being the default and highest level of optimizations.

  Option type: unsigned int. Applies to: compiler only

• JIT_TARGET_FROM_CUCONTEXT - No option value required. Determines the target based on the current attached context (default).

  Option type: No option value needed. Applies to: compiler and linker

• JIT_TARGET - Target is chosen based on supplied CUjit_target. Cannot be combined with JIT_THREADS_PER_BLOCK.

  Option type: unsigned int for enumerated type CUjit_target. Applies to: compiler and linker

• JIT_FALLBACK_STRATEGY - Specifies choice of fallback strategy if matching cubin is not found.

  Choice is based on supplied CUjit_fallback. This option cannot be used with cuLink* APIs as the linker requires exact matches.

  Option type: unsigned int for enumerated type CUjit_fallback. Applies to: compiler only

• JIT_GENERATE_DEBUG_INFO - Specifies whether to create debug information in output (-g) (0: false, default).

  Option type: int. Applies to: compiler and linker

• JIT_LOG_VERBOSE - Generate verbose log messages (0: false, default).

  Option type: int. Applies to: compiler and linker

• JIT_GENERATE_LINE_INFO - Generate line number information (-lineinfo) (0: false, default).

  Option type: int. Applies to: compiler only

• JIT_CACHE_MODE - Specifies whether to enable caching explicitly (-dlcm). Choice is based on supplied CUjit_cacheMode_enum.

  Option type: unsigned int for enumerated type CUjit_cacheMode_enum. Applies to: compiler only

• JIT_NEW_SM3X_OPT - Used for internal purposes only, in this version of CUDA.
• JIT_FAST_COMPILE - Used for internal purposes only, in this version of CUDA.
• JIT_GLOBAL_SYMBOL_NAMES - Array of device symbol names that will be relocated to the corresponing host addresses stored in JIT_GLOBAL_SYMBOL_ADDRESSES.

  Must contain JIT_GLOBAL_SYMBOL_COUNT entries. When loding a device module, driver will relocate all encountered unresolved symbols to the host addresses. It is only allowed to register symbols that correspond to unresolved global variables. It is illegal to register the same device symbol at multiple addresses.

  Option type: const char **. Applies to: dynamic linker only

• JIT_GLOBAL_SYMBOL_ADDRESSES - Array of host addresses that will be used to relocate corresponding device symbols stored in JIT_GLOBAL_SYMBOL_NAMES.

  Must contain JIT_GLOBAL_SYMBOL_COUNT entries.

  Option type: void **. Applies to: dynamic linker only

• JIT_GLOBAL_SYMBOL_COUNT - Number of entries in JIT_GLOBAL_SYMBOL_NAMES and JIT_GLOBAL_SYMBOL_ADDRESSES arrays.

  Option type: unsigned int. Applies to: dynamic linker only

• JIT_LTO - Enable link-time optimization (-dlto) for device code (0: false, default)

  Option type: int. Applies to: compiler and linker

• JIT_FTZ - Control single-precision denormals (-ftz) support (0: false, default).
  • 1 : flushes denormal values to zero
  • 0 : preserves denormal values

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_PREC_DIV - Control single-precision floating-point division and reciprocals (-prec-div) support (1: true, default).
  • 1 : Enables the IEEE round-to-nearest mode
  • 0 : Enables the fast approximation mode

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_PREC_SQRT - Control single-precision floating-point square root (-prec-sqrt) support (1: true, default).
  • 1 : Enables the IEEE round-to-nearest mode
  • 0 : Enables the fast approximation mode

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_FMA - Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_NUM_OPTIONS - Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

See Also:

• Constant Field Values

CU_JIT_NEW_SM3X_OPT

public static final int CU_JIT_NEW_SM3X_OPT

Online compiler and linker options. (CUjit_option)

Enum values:

• JIT_MAX_REGISTERS - Max number of registers that a thread may use.

  Option type: unsigned int. Applies to: compiler only

• JIT_THREADS_PER_BLOCK - IN: Specifies minimum number of threads per block to target compilation for

  OUT: Returns the number of threads the compiler actually targeted.

  This restricts the resource utilization fo the compiler (e.g. max registers) such that a block with the given number of threads should be able to launch based on register limitations. Note, this option does not currently take into account any other resource limitations, such as shared memory utilization.

  Cannot be combined with JIT_TARGET. Option type: unsigned int. Applies to: compiler only

• JIT_WALL_TIME - Overwrites the option value with the total wall clock time, in milliseconds, spent in the compiler and linker.

  Option type: float. Applies to: compiler and linker

• JIT_INFO_LOG_BUFFER - Pointer to a buffer in which to print any log messages that are informational in nature (the buffer size is specified via option JIT_INFO_LOG_BUFFER_SIZE_BYTES).

  Option type: char *. Applies to: compiler and linker

• JIT_INFO_LOG_BUFFER_SIZE_BYTES - IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).

  OUT: Amount of log buffer filled with messages.

  Option type: unsigned int. Applies to: compiler and linker

• JIT_ERROR_LOG_BUFFER - Pointer to a buffer in which to print any log messages that reflect errors (the buffer size is specified via option JIT_ERROR_LOG_BUFFER_SIZE_BYTES).

  Option type: char *. Applies to: compiler and linker

• JIT_ERROR_LOG_BUFFER_SIZE_BYTES - IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).

  OUT: Amount of log buffer filled with messages.

  Option type: unsigned int. Applies to: compiler and linker

• JIT_OPTIMIZATION_LEVEL - Level of optimizations to apply to generated code (0 - 4), with 4 being the default and highest level of optimizations.

  Option type: unsigned int. Applies to: compiler only

• JIT_TARGET_FROM_CUCONTEXT - No option value required. Determines the target based on the current attached context (default).

  Option type: No option value needed. Applies to: compiler and linker

• JIT_TARGET - Target is chosen based on supplied CUjit_target. Cannot be combined with JIT_THREADS_PER_BLOCK.

  Option type: unsigned int for enumerated type CUjit_target. Applies to: compiler and linker

• JIT_FALLBACK_STRATEGY - Specifies choice of fallback strategy if matching cubin is not found.

  Choice is based on supplied CUjit_fallback. This option cannot be used with cuLink* APIs as the linker requires exact matches.

  Option type: unsigned int for enumerated type CUjit_fallback. Applies to: compiler only

• JIT_GENERATE_DEBUG_INFO - Specifies whether to create debug information in output (-g) (0: false, default).

  Option type: int. Applies to: compiler and linker

• JIT_LOG_VERBOSE - Generate verbose log messages (0: false, default).

  Option type: int. Applies to: compiler and linker

• JIT_GENERATE_LINE_INFO - Generate line number information (-lineinfo) (0: false, default).

  Option type: int. Applies to: compiler only

• JIT_CACHE_MODE - Specifies whether to enable caching explicitly (-dlcm). Choice is based on supplied CUjit_cacheMode_enum.

  Option type: unsigned int for enumerated type CUjit_cacheMode_enum. Applies to: compiler only

• JIT_NEW_SM3X_OPT - Used for internal purposes only, in this version of CUDA.
• JIT_FAST_COMPILE - Used for internal purposes only, in this version of CUDA.
• JIT_GLOBAL_SYMBOL_NAMES - Array of device symbol names that will be relocated to the corresponing host addresses stored in JIT_GLOBAL_SYMBOL_ADDRESSES.

  Must contain JIT_GLOBAL_SYMBOL_COUNT entries. When loding a device module, driver will relocate all encountered unresolved symbols to the host addresses. It is only allowed to register symbols that correspond to unresolved global variables. It is illegal to register the same device symbol at multiple addresses.

  Option type: const char **. Applies to: dynamic linker only

• JIT_GLOBAL_SYMBOL_ADDRESSES - Array of host addresses that will be used to relocate corresponding device symbols stored in JIT_GLOBAL_SYMBOL_NAMES.

  Must contain JIT_GLOBAL_SYMBOL_COUNT entries.

  Option type: void **. Applies to: dynamic linker only

• JIT_GLOBAL_SYMBOL_COUNT - Number of entries in JIT_GLOBAL_SYMBOL_NAMES and JIT_GLOBAL_SYMBOL_ADDRESSES arrays.

  Option type: unsigned int. Applies to: dynamic linker only

• JIT_LTO - Enable link-time optimization (-dlto) for device code (0: false, default)

  Option type: int. Applies to: compiler and linker

• JIT_FTZ - Control single-precision denormals (-ftz) support (0: false, default).
  • 1 : flushes denormal values to zero
  • 0 : preserves denormal values

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_PREC_DIV - Control single-precision floating-point division and reciprocals (-prec-div) support (1: true, default).
  • 1 : Enables the IEEE round-to-nearest mode
  • 0 : Enables the fast approximation mode

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_PREC_SQRT - Control single-precision floating-point square root (-prec-sqrt) support (1: true, default).
  • 1 : Enables the IEEE round-to-nearest mode
  • 0 : Enables the fast approximation mode

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_FMA - Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_NUM_OPTIONS - Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

See Also:

• Constant Field Values

CU_JIT_FAST_COMPILE

public static final int CU_JIT_FAST_COMPILE

Online compiler and linker options. (CUjit_option)

Enum values:

• JIT_MAX_REGISTERS - Max number of registers that a thread may use.

  Option type: unsigned int. Applies to: compiler only

• JIT_THREADS_PER_BLOCK - IN: Specifies minimum number of threads per block to target compilation for

  OUT: Returns the number of threads the compiler actually targeted.

  This restricts the resource utilization fo the compiler (e.g. max registers) such that a block with the given number of threads should be able to launch based on register limitations. Note, this option does not currently take into account any other resource limitations, such as shared memory utilization.

  Cannot be combined with JIT_TARGET. Option type: unsigned int. Applies to: compiler only

• JIT_WALL_TIME - Overwrites the option value with the total wall clock time, in milliseconds, spent in the compiler and linker.

  Option type: float. Applies to: compiler and linker

• JIT_INFO_LOG_BUFFER - Pointer to a buffer in which to print any log messages that are informational in nature (the buffer size is specified via option JIT_INFO_LOG_BUFFER_SIZE_BYTES).

  Option type: char *. Applies to: compiler and linker

• JIT_INFO_LOG_BUFFER_SIZE_BYTES - IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).

  OUT: Amount of log buffer filled with messages.

  Option type: unsigned int. Applies to: compiler and linker

• JIT_ERROR_LOG_BUFFER - Pointer to a buffer in which to print any log messages that reflect errors (the buffer size is specified via option JIT_ERROR_LOG_BUFFER_SIZE_BYTES).

  Option type: char *. Applies to: compiler and linker

• JIT_ERROR_LOG_BUFFER_SIZE_BYTES - IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).

  OUT: Amount of log buffer filled with messages.

  Option type: unsigned int. Applies to: compiler and linker

• JIT_OPTIMIZATION_LEVEL - Level of optimizations to apply to generated code (0 - 4), with 4 being the default and highest level of optimizations.

  Option type: unsigned int. Applies to: compiler only

• JIT_TARGET_FROM_CUCONTEXT - No option value required. Determines the target based on the current attached context (default).

  Option type: No option value needed. Applies to: compiler and linker

• JIT_TARGET - Target is chosen based on supplied CUjit_target. Cannot be combined with JIT_THREADS_PER_BLOCK.

  Option type: unsigned int for enumerated type CUjit_target. Applies to: compiler and linker

• JIT_FALLBACK_STRATEGY - Specifies choice of fallback strategy if matching cubin is not found.

  Choice is based on supplied CUjit_fallback. This option cannot be used with cuLink* APIs as the linker requires exact matches.

  Option type: unsigned int for enumerated type CUjit_fallback. Applies to: compiler only

• JIT_GENERATE_DEBUG_INFO - Specifies whether to create debug information in output (-g) (0: false, default).

  Option type: int. Applies to: compiler and linker

• JIT_LOG_VERBOSE - Generate verbose log messages (0: false, default).

  Option type: int. Applies to: compiler and linker

• JIT_GENERATE_LINE_INFO - Generate line number information (-lineinfo) (0: false, default).

  Option type: int. Applies to: compiler only

• JIT_CACHE_MODE - Specifies whether to enable caching explicitly (-dlcm). Choice is based on supplied CUjit_cacheMode_enum.

  Option type: unsigned int for enumerated type CUjit_cacheMode_enum. Applies to: compiler only

• JIT_NEW_SM3X_OPT - Used for internal purposes only, in this version of CUDA.
• JIT_FAST_COMPILE - Used for internal purposes only, in this version of CUDA.
• JIT_GLOBAL_SYMBOL_NAMES - Array of device symbol names that will be relocated to the corresponing host addresses stored in JIT_GLOBAL_SYMBOL_ADDRESSES.

  Must contain JIT_GLOBAL_SYMBOL_COUNT entries. When loding a device module, driver will relocate all encountered unresolved symbols to the host addresses. It is only allowed to register symbols that correspond to unresolved global variables. It is illegal to register the same device symbol at multiple addresses.

  Option type: const char **. Applies to: dynamic linker only

• JIT_GLOBAL_SYMBOL_ADDRESSES - Array of host addresses that will be used to relocate corresponding device symbols stored in JIT_GLOBAL_SYMBOL_NAMES.

  Must contain JIT_GLOBAL_SYMBOL_COUNT entries.

  Option type: void **. Applies to: dynamic linker only

• JIT_GLOBAL_SYMBOL_COUNT - Number of entries in JIT_GLOBAL_SYMBOL_NAMES and JIT_GLOBAL_SYMBOL_ADDRESSES arrays.

  Option type: unsigned int. Applies to: dynamic linker only

• JIT_LTO - Enable link-time optimization (-dlto) for device code (0: false, default)

  Option type: int. Applies to: compiler and linker

• JIT_FTZ - Control single-precision denormals (-ftz) support (0: false, default).
  • 1 : flushes denormal values to zero
  • 0 : preserves denormal values

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_PREC_DIV - Control single-precision floating-point division and reciprocals (-prec-div) support (1: true, default).
  • 1 : Enables the IEEE round-to-nearest mode
  • 0 : Enables the fast approximation mode

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_PREC_SQRT - Control single-precision floating-point square root (-prec-sqrt) support (1: true, default).
  • 1 : Enables the IEEE round-to-nearest mode
  • 0 : Enables the fast approximation mode

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_FMA - Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_NUM_OPTIONS - Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

See Also:

• Constant Field Values

CU_JIT_GLOBAL_SYMBOL_NAMES

public static final int CU_JIT_GLOBAL_SYMBOL_NAMES

Online compiler and linker options. (CUjit_option)

Enum values:

• JIT_MAX_REGISTERS - Max number of registers that a thread may use.

  Option type: unsigned int. Applies to: compiler only

• JIT_THREADS_PER_BLOCK - IN: Specifies minimum number of threads per block to target compilation for

  OUT: Returns the number of threads the compiler actually targeted.

  This restricts the resource utilization fo the compiler (e.g. max registers) such that a block with the given number of threads should be able to launch based on register limitations. Note, this option does not currently take into account any other resource limitations, such as shared memory utilization.

  Cannot be combined with JIT_TARGET. Option type: unsigned int. Applies to: compiler only

• JIT_WALL_TIME - Overwrites the option value with the total wall clock time, in milliseconds, spent in the compiler and linker.

  Option type: float. Applies to: compiler and linker

• JIT_INFO_LOG_BUFFER - Pointer to a buffer in which to print any log messages that are informational in nature (the buffer size is specified via option JIT_INFO_LOG_BUFFER_SIZE_BYTES).

  Option type: char *. Applies to: compiler and linker

• JIT_INFO_LOG_BUFFER_SIZE_BYTES - IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).

  OUT: Amount of log buffer filled with messages.

  Option type: unsigned int. Applies to: compiler and linker

• JIT_ERROR_LOG_BUFFER - Pointer to a buffer in which to print any log messages that reflect errors (the buffer size is specified via option JIT_ERROR_LOG_BUFFER_SIZE_BYTES).

  Option type: char *. Applies to: compiler and linker

• JIT_ERROR_LOG_BUFFER_SIZE_BYTES - IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).

  OUT: Amount of log buffer filled with messages.

  Option type: unsigned int. Applies to: compiler and linker

• JIT_OPTIMIZATION_LEVEL - Level of optimizations to apply to generated code (0 - 4), with 4 being the default and highest level of optimizations.

  Option type: unsigned int. Applies to: compiler only

• JIT_TARGET_FROM_CUCONTEXT - No option value required. Determines the target based on the current attached context (default).

  Option type: No option value needed. Applies to: compiler and linker

• JIT_TARGET - Target is chosen based on supplied CUjit_target. Cannot be combined with JIT_THREADS_PER_BLOCK.

  Option type: unsigned int for enumerated type CUjit_target. Applies to: compiler and linker

• JIT_FALLBACK_STRATEGY - Specifies choice of fallback strategy if matching cubin is not found.

  Choice is based on supplied CUjit_fallback. This option cannot be used with cuLink* APIs as the linker requires exact matches.

  Option type: unsigned int for enumerated type CUjit_fallback. Applies to: compiler only

• JIT_GENERATE_DEBUG_INFO - Specifies whether to create debug information in output (-g) (0: false, default).

  Option type: int. Applies to: compiler and linker

• JIT_LOG_VERBOSE - Generate verbose log messages (0: false, default).

  Option type: int. Applies to: compiler and linker

• JIT_GENERATE_LINE_INFO - Generate line number information (-lineinfo) (0: false, default).

  Option type: int. Applies to: compiler only

• JIT_CACHE_MODE - Specifies whether to enable caching explicitly (-dlcm). Choice is based on supplied CUjit_cacheMode_enum.

  Option type: unsigned int for enumerated type CUjit_cacheMode_enum. Applies to: compiler only

• JIT_NEW_SM3X_OPT - Used for internal purposes only, in this version of CUDA.
• JIT_FAST_COMPILE - Used for internal purposes only, in this version of CUDA.
• JIT_GLOBAL_SYMBOL_NAMES - Array of device symbol names that will be relocated to the corresponing host addresses stored in JIT_GLOBAL_SYMBOL_ADDRESSES.

  Must contain JIT_GLOBAL_SYMBOL_COUNT entries. When loding a device module, driver will relocate all encountered unresolved symbols to the host addresses. It is only allowed to register symbols that correspond to unresolved global variables. It is illegal to register the same device symbol at multiple addresses.

  Option type: const char **. Applies to: dynamic linker only

• JIT_GLOBAL_SYMBOL_ADDRESSES - Array of host addresses that will be used to relocate corresponding device symbols stored in JIT_GLOBAL_SYMBOL_NAMES.

  Must contain JIT_GLOBAL_SYMBOL_COUNT entries.

  Option type: void **. Applies to: dynamic linker only

• JIT_GLOBAL_SYMBOL_COUNT - Number of entries in JIT_GLOBAL_SYMBOL_NAMES and JIT_GLOBAL_SYMBOL_ADDRESSES arrays.

  Option type: unsigned int. Applies to: dynamic linker only

• JIT_LTO - Enable link-time optimization (-dlto) for device code (0: false, default)

  Option type: int. Applies to: compiler and linker

• JIT_FTZ - Control single-precision denormals (-ftz) support (0: false, default).
  • 1 : flushes denormal values to zero
  • 0 : preserves denormal values

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_PREC_DIV - Control single-precision floating-point division and reciprocals (-prec-div) support (1: true, default).
  • 1 : Enables the IEEE round-to-nearest mode
  • 0 : Enables the fast approximation mode

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_PREC_SQRT - Control single-precision floating-point square root (-prec-sqrt) support (1: true, default).
  • 1 : Enables the IEEE round-to-nearest mode
  • 0 : Enables the fast approximation mode

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_FMA - Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_NUM_OPTIONS - Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

See Also:

• Constant Field Values

CU_JIT_GLOBAL_SYMBOL_ADDRESSES

public static final int CU_JIT_GLOBAL_SYMBOL_ADDRESSES

Online compiler and linker options. (CUjit_option)

Enum values:

• JIT_MAX_REGISTERS - Max number of registers that a thread may use.

  Option type: unsigned int. Applies to: compiler only

• JIT_THREADS_PER_BLOCK - IN: Specifies minimum number of threads per block to target compilation for

  OUT: Returns the number of threads the compiler actually targeted.

  This restricts the resource utilization fo the compiler (e.g. max registers) such that a block with the given number of threads should be able to launch based on register limitations. Note, this option does not currently take into account any other resource limitations, such as shared memory utilization.

  Cannot be combined with JIT_TARGET. Option type: unsigned int. Applies to: compiler only

• JIT_WALL_TIME - Overwrites the option value with the total wall clock time, in milliseconds, spent in the compiler and linker.

  Option type: float. Applies to: compiler and linker

• JIT_INFO_LOG_BUFFER - Pointer to a buffer in which to print any log messages that are informational in nature (the buffer size is specified via option JIT_INFO_LOG_BUFFER_SIZE_BYTES).

  Option type: char *. Applies to: compiler and linker

• JIT_INFO_LOG_BUFFER_SIZE_BYTES - IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).

  OUT: Amount of log buffer filled with messages.

  Option type: unsigned int. Applies to: compiler and linker

• JIT_ERROR_LOG_BUFFER - Pointer to a buffer in which to print any log messages that reflect errors (the buffer size is specified via option JIT_ERROR_LOG_BUFFER_SIZE_BYTES).

  Option type: char *. Applies to: compiler and linker

• JIT_ERROR_LOG_BUFFER_SIZE_BYTES - IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).

  OUT: Amount of log buffer filled with messages.

  Option type: unsigned int. Applies to: compiler and linker

• JIT_OPTIMIZATION_LEVEL - Level of optimizations to apply to generated code (0 - 4), with 4 being the default and highest level of optimizations.

  Option type: unsigned int. Applies to: compiler only

• JIT_TARGET_FROM_CUCONTEXT - No option value required. Determines the target based on the current attached context (default).

  Option type: No option value needed. Applies to: compiler and linker

• JIT_TARGET - Target is chosen based on supplied CUjit_target. Cannot be combined with JIT_THREADS_PER_BLOCK.

  Option type: unsigned int for enumerated type CUjit_target. Applies to: compiler and linker

• JIT_FALLBACK_STRATEGY - Specifies choice of fallback strategy if matching cubin is not found.

  Choice is based on supplied CUjit_fallback. This option cannot be used with cuLink* APIs as the linker requires exact matches.

  Option type: unsigned int for enumerated type CUjit_fallback. Applies to: compiler only

• JIT_GENERATE_DEBUG_INFO - Specifies whether to create debug information in output (-g) (0: false, default).

  Option type: int. Applies to: compiler and linker

• JIT_LOG_VERBOSE - Generate verbose log messages (0: false, default).

  Option type: int. Applies to: compiler and linker

• JIT_GENERATE_LINE_INFO - Generate line number information (-lineinfo) (0: false, default).

  Option type: int. Applies to: compiler only

• JIT_CACHE_MODE - Specifies whether to enable caching explicitly (-dlcm). Choice is based on supplied CUjit_cacheMode_enum.

  Option type: unsigned int for enumerated type CUjit_cacheMode_enum. Applies to: compiler only

• JIT_NEW_SM3X_OPT - Used for internal purposes only, in this version of CUDA.
• JIT_FAST_COMPILE - Used for internal purposes only, in this version of CUDA.
• JIT_GLOBAL_SYMBOL_NAMES - Array of device symbol names that will be relocated to the corresponing host addresses stored in JIT_GLOBAL_SYMBOL_ADDRESSES.

  Must contain JIT_GLOBAL_SYMBOL_COUNT entries. When loding a device module, driver will relocate all encountered unresolved symbols to the host addresses. It is only allowed to register symbols that correspond to unresolved global variables. It is illegal to register the same device symbol at multiple addresses.

  Option type: const char **. Applies to: dynamic linker only

• JIT_GLOBAL_SYMBOL_ADDRESSES - Array of host addresses that will be used to relocate corresponding device symbols stored in JIT_GLOBAL_SYMBOL_NAMES.

  Must contain JIT_GLOBAL_SYMBOL_COUNT entries.

  Option type: void **. Applies to: dynamic linker only

• JIT_GLOBAL_SYMBOL_COUNT - Number of entries in JIT_GLOBAL_SYMBOL_NAMES and JIT_GLOBAL_SYMBOL_ADDRESSES arrays.

  Option type: unsigned int. Applies to: dynamic linker only

• JIT_LTO - Enable link-time optimization (-dlto) for device code (0: false, default)

  Option type: int. Applies to: compiler and linker

• JIT_FTZ - Control single-precision denormals (-ftz) support (0: false, default).
  • 1 : flushes denormal values to zero
  • 0 : preserves denormal values

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_PREC_DIV - Control single-precision floating-point division and reciprocals (-prec-div) support (1: true, default).
  • 1 : Enables the IEEE round-to-nearest mode
  • 0 : Enables the fast approximation mode

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_PREC_SQRT - Control single-precision floating-point square root (-prec-sqrt) support (1: true, default).
  • 1 : Enables the IEEE round-to-nearest mode
  • 0 : Enables the fast approximation mode

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_FMA - Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_NUM_OPTIONS - Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

See Also:

• Constant Field Values

CU_JIT_GLOBAL_SYMBOL_COUNT

public static final int CU_JIT_GLOBAL_SYMBOL_COUNT

Online compiler and linker options. (CUjit_option)

Enum values:

• JIT_MAX_REGISTERS - Max number of registers that a thread may use.

  Option type: unsigned int. Applies to: compiler only

• JIT_THREADS_PER_BLOCK - IN: Specifies minimum number of threads per block to target compilation for

  OUT: Returns the number of threads the compiler actually targeted.

  This restricts the resource utilization fo the compiler (e.g. max registers) such that a block with the given number of threads should be able to launch based on register limitations. Note, this option does not currently take into account any other resource limitations, such as shared memory utilization.

  Cannot be combined with JIT_TARGET. Option type: unsigned int. Applies to: compiler only

• JIT_WALL_TIME - Overwrites the option value with the total wall clock time, in milliseconds, spent in the compiler and linker.

  Option type: float. Applies to: compiler and linker

• JIT_INFO_LOG_BUFFER - Pointer to a buffer in which to print any log messages that are informational in nature (the buffer size is specified via option JIT_INFO_LOG_BUFFER_SIZE_BYTES).

  Option type: char *. Applies to: compiler and linker

• JIT_INFO_LOG_BUFFER_SIZE_BYTES - IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).

  OUT: Amount of log buffer filled with messages.

  Option type: unsigned int. Applies to: compiler and linker

• JIT_ERROR_LOG_BUFFER - Pointer to a buffer in which to print any log messages that reflect errors (the buffer size is specified via option JIT_ERROR_LOG_BUFFER_SIZE_BYTES).

  Option type: char *. Applies to: compiler and linker

• JIT_ERROR_LOG_BUFFER_SIZE_BYTES - IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).

  OUT: Amount of log buffer filled with messages.

  Option type: unsigned int. Applies to: compiler and linker

• JIT_OPTIMIZATION_LEVEL - Level of optimizations to apply to generated code (0 - 4), with 4 being the default and highest level of optimizations.

  Option type: unsigned int. Applies to: compiler only

• JIT_TARGET_FROM_CUCONTEXT - No option value required. Determines the target based on the current attached context (default).

  Option type: No option value needed. Applies to: compiler and linker

• JIT_TARGET - Target is chosen based on supplied CUjit_target. Cannot be combined with JIT_THREADS_PER_BLOCK.

  Option type: unsigned int for enumerated type CUjit_target. Applies to: compiler and linker

• JIT_FALLBACK_STRATEGY - Specifies choice of fallback strategy if matching cubin is not found.

  Choice is based on supplied CUjit_fallback. This option cannot be used with cuLink* APIs as the linker requires exact matches.

  Option type: unsigned int for enumerated type CUjit_fallback. Applies to: compiler only

• JIT_GENERATE_DEBUG_INFO - Specifies whether to create debug information in output (-g) (0: false, default).

  Option type: int. Applies to: compiler and linker

• JIT_LOG_VERBOSE - Generate verbose log messages (0: false, default).

  Option type: int. Applies to: compiler and linker

• JIT_GENERATE_LINE_INFO - Generate line number information (-lineinfo) (0: false, default).

  Option type: int. Applies to: compiler only

• JIT_CACHE_MODE - Specifies whether to enable caching explicitly (-dlcm). Choice is based on supplied CUjit_cacheMode_enum.

  Option type: unsigned int for enumerated type CUjit_cacheMode_enum. Applies to: compiler only

• JIT_NEW_SM3X_OPT - Used for internal purposes only, in this version of CUDA.
• JIT_FAST_COMPILE - Used for internal purposes only, in this version of CUDA.
• JIT_GLOBAL_SYMBOL_NAMES - Array of device symbol names that will be relocated to the corresponing host addresses stored in JIT_GLOBAL_SYMBOL_ADDRESSES.

  Must contain JIT_GLOBAL_SYMBOL_COUNT entries. When loding a device module, driver will relocate all encountered unresolved symbols to the host addresses. It is only allowed to register symbols that correspond to unresolved global variables. It is illegal to register the same device symbol at multiple addresses.

  Option type: const char **. Applies to: dynamic linker only

• JIT_GLOBAL_SYMBOL_ADDRESSES - Array of host addresses that will be used to relocate corresponding device symbols stored in JIT_GLOBAL_SYMBOL_NAMES.

  Must contain JIT_GLOBAL_SYMBOL_COUNT entries.

  Option type: void **. Applies to: dynamic linker only

• JIT_GLOBAL_SYMBOL_COUNT - Number of entries in JIT_GLOBAL_SYMBOL_NAMES and JIT_GLOBAL_SYMBOL_ADDRESSES arrays.

  Option type: unsigned int. Applies to: dynamic linker only

• JIT_LTO - Enable link-time optimization (-dlto) for device code (0: false, default)

  Option type: int. Applies to: compiler and linker

• JIT_FTZ - Control single-precision denormals (-ftz) support (0: false, default).
  • 1 : flushes denormal values to zero
  • 0 : preserves denormal values

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_PREC_DIV - Control single-precision floating-point division and reciprocals (-prec-div) support (1: true, default).
  • 1 : Enables the IEEE round-to-nearest mode
  • 0 : Enables the fast approximation mode

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_PREC_SQRT - Control single-precision floating-point square root (-prec-sqrt) support (1: true, default).
  • 1 : Enables the IEEE round-to-nearest mode
  • 0 : Enables the fast approximation mode

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_FMA - Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_NUM_OPTIONS - Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

See Also:

• Constant Field Values

CU_JIT_LTO

public static final int CU_JIT_LTO

Online compiler and linker options. (CUjit_option)

Enum values:

• JIT_MAX_REGISTERS - Max number of registers that a thread may use.

  Option type: unsigned int. Applies to: compiler only

• JIT_THREADS_PER_BLOCK - IN: Specifies minimum number of threads per block to target compilation for

  OUT: Returns the number of threads the compiler actually targeted.

  This restricts the resource utilization fo the compiler (e.g. max registers) such that a block with the given number of threads should be able to launch based on register limitations. Note, this option does not currently take into account any other resource limitations, such as shared memory utilization.

  Cannot be combined with JIT_TARGET. Option type: unsigned int. Applies to: compiler only

• JIT_WALL_TIME - Overwrites the option value with the total wall clock time, in milliseconds, spent in the compiler and linker.

  Option type: float. Applies to: compiler and linker

• JIT_INFO_LOG_BUFFER - Pointer to a buffer in which to print any log messages that are informational in nature (the buffer size is specified via option JIT_INFO_LOG_BUFFER_SIZE_BYTES).

  Option type: char *. Applies to: compiler and linker

• JIT_INFO_LOG_BUFFER_SIZE_BYTES - IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).

  OUT: Amount of log buffer filled with messages.

  Option type: unsigned int. Applies to: compiler and linker

• JIT_ERROR_LOG_BUFFER - Pointer to a buffer in which to print any log messages that reflect errors (the buffer size is specified via option JIT_ERROR_LOG_BUFFER_SIZE_BYTES).

  Option type: char *. Applies to: compiler and linker

• JIT_ERROR_LOG_BUFFER_SIZE_BYTES - IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).

  OUT: Amount of log buffer filled with messages.

  Option type: unsigned int. Applies to: compiler and linker

• JIT_OPTIMIZATION_LEVEL - Level of optimizations to apply to generated code (0 - 4), with 4 being the default and highest level of optimizations.

  Option type: unsigned int. Applies to: compiler only

• JIT_TARGET_FROM_CUCONTEXT - No option value required. Determines the target based on the current attached context (default).

  Option type: No option value needed. Applies to: compiler and linker

• JIT_TARGET - Target is chosen based on supplied CUjit_target. Cannot be combined with JIT_THREADS_PER_BLOCK.

  Option type: unsigned int for enumerated type CUjit_target. Applies to: compiler and linker

• JIT_FALLBACK_STRATEGY - Specifies choice of fallback strategy if matching cubin is not found.

  Choice is based on supplied CUjit_fallback. This option cannot be used with cuLink* APIs as the linker requires exact matches.

  Option type: unsigned int for enumerated type CUjit_fallback. Applies to: compiler only

• JIT_GENERATE_DEBUG_INFO - Specifies whether to create debug information in output (-g) (0: false, default).

  Option type: int. Applies to: compiler and linker

• JIT_LOG_VERBOSE - Generate verbose log messages (0: false, default).

  Option type: int. Applies to: compiler and linker

• JIT_GENERATE_LINE_INFO - Generate line number information (-lineinfo) (0: false, default).

  Option type: int. Applies to: compiler only

• JIT_CACHE_MODE - Specifies whether to enable caching explicitly (-dlcm). Choice is based on supplied CUjit_cacheMode_enum.

  Option type: unsigned int for enumerated type CUjit_cacheMode_enum. Applies to: compiler only

• JIT_NEW_SM3X_OPT - Used for internal purposes only, in this version of CUDA.
• JIT_FAST_COMPILE - Used for internal purposes only, in this version of CUDA.
• JIT_GLOBAL_SYMBOL_NAMES - Array of device symbol names that will be relocated to the corresponing host addresses stored in JIT_GLOBAL_SYMBOL_ADDRESSES.

  Must contain JIT_GLOBAL_SYMBOL_COUNT entries. When loding a device module, driver will relocate all encountered unresolved symbols to the host addresses. It is only allowed to register symbols that correspond to unresolved global variables. It is illegal to register the same device symbol at multiple addresses.

  Option type: const char **. Applies to: dynamic linker only

• JIT_GLOBAL_SYMBOL_ADDRESSES - Array of host addresses that will be used to relocate corresponding device symbols stored in JIT_GLOBAL_SYMBOL_NAMES.

  Must contain JIT_GLOBAL_SYMBOL_COUNT entries.

  Option type: void **. Applies to: dynamic linker only

• JIT_GLOBAL_SYMBOL_COUNT - Number of entries in JIT_GLOBAL_SYMBOL_NAMES and JIT_GLOBAL_SYMBOL_ADDRESSES arrays.

  Option type: unsigned int. Applies to: dynamic linker only

• JIT_LTO - Enable link-time optimization (-dlto) for device code (0: false, default)

  Option type: int. Applies to: compiler and linker

• JIT_FTZ - Control single-precision denormals (-ftz) support (0: false, default).
  • 1 : flushes denormal values to zero
  • 0 : preserves denormal values

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_PREC_DIV - Control single-precision floating-point division and reciprocals (-prec-div) support (1: true, default).
  • 1 : Enables the IEEE round-to-nearest mode
  • 0 : Enables the fast approximation mode

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_PREC_SQRT - Control single-precision floating-point square root (-prec-sqrt) support (1: true, default).
  • 1 : Enables the IEEE round-to-nearest mode
  • 0 : Enables the fast approximation mode

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_FMA - Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_NUM_OPTIONS - Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

See Also:

• Constant Field Values

CU_JIT_FTZ

public static final int CU_JIT_FTZ

Online compiler and linker options. (CUjit_option)

Enum values:

• JIT_MAX_REGISTERS - Max number of registers that a thread may use.

  Option type: unsigned int. Applies to: compiler only

• JIT_THREADS_PER_BLOCK - IN: Specifies minimum number of threads per block to target compilation for

  OUT: Returns the number of threads the compiler actually targeted.

  This restricts the resource utilization fo the compiler (e.g. max registers) such that a block with the given number of threads should be able to launch based on register limitations. Note, this option does not currently take into account any other resource limitations, such as shared memory utilization.

  Cannot be combined with JIT_TARGET. Option type: unsigned int. Applies to: compiler only

• JIT_WALL_TIME - Overwrites the option value with the total wall clock time, in milliseconds, spent in the compiler and linker.

  Option type: float. Applies to: compiler and linker

• JIT_INFO_LOG_BUFFER - Pointer to a buffer in which to print any log messages that are informational in nature (the buffer size is specified via option JIT_INFO_LOG_BUFFER_SIZE_BYTES).

  Option type: char *. Applies to: compiler and linker

• JIT_INFO_LOG_BUFFER_SIZE_BYTES - IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).

  OUT: Amount of log buffer filled with messages.

  Option type: unsigned int. Applies to: compiler and linker

• JIT_ERROR_LOG_BUFFER - Pointer to a buffer in which to print any log messages that reflect errors (the buffer size is specified via option JIT_ERROR_LOG_BUFFER_SIZE_BYTES).

  Option type: char *. Applies to: compiler and linker

• JIT_ERROR_LOG_BUFFER_SIZE_BYTES - IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).

  OUT: Amount of log buffer filled with messages.

  Option type: unsigned int. Applies to: compiler and linker

• JIT_OPTIMIZATION_LEVEL - Level of optimizations to apply to generated code (0 - 4), with 4 being the default and highest level of optimizations.

  Option type: unsigned int. Applies to: compiler only

• JIT_TARGET_FROM_CUCONTEXT - No option value required. Determines the target based on the current attached context (default).

  Option type: No option value needed. Applies to: compiler and linker

• JIT_TARGET - Target is chosen based on supplied CUjit_target. Cannot be combined with JIT_THREADS_PER_BLOCK.

  Option type: unsigned int for enumerated type CUjit_target. Applies to: compiler and linker

• JIT_FALLBACK_STRATEGY - Specifies choice of fallback strategy if matching cubin is not found.

  Choice is based on supplied CUjit_fallback. This option cannot be used with cuLink* APIs as the linker requires exact matches.

  Option type: unsigned int for enumerated type CUjit_fallback. Applies to: compiler only

• JIT_GENERATE_DEBUG_INFO - Specifies whether to create debug information in output (-g) (0: false, default).

  Option type: int. Applies to: compiler and linker

• JIT_LOG_VERBOSE - Generate verbose log messages (0: false, default).

  Option type: int. Applies to: compiler and linker

• JIT_GENERATE_LINE_INFO - Generate line number information (-lineinfo) (0: false, default).

  Option type: int. Applies to: compiler only

• JIT_CACHE_MODE - Specifies whether to enable caching explicitly (-dlcm). Choice is based on supplied CUjit_cacheMode_enum.

  Option type: unsigned int for enumerated type CUjit_cacheMode_enum. Applies to: compiler only

• JIT_NEW_SM3X_OPT - Used for internal purposes only, in this version of CUDA.
• JIT_FAST_COMPILE - Used for internal purposes only, in this version of CUDA.
• JIT_GLOBAL_SYMBOL_NAMES - Array of device symbol names that will be relocated to the corresponing host addresses stored in JIT_GLOBAL_SYMBOL_ADDRESSES.

  Must contain JIT_GLOBAL_SYMBOL_COUNT entries. When loding a device module, driver will relocate all encountered unresolved symbols to the host addresses. It is only allowed to register symbols that correspond to unresolved global variables. It is illegal to register the same device symbol at multiple addresses.

  Option type: const char **. Applies to: dynamic linker only

• JIT_GLOBAL_SYMBOL_ADDRESSES - Array of host addresses that will be used to relocate corresponding device symbols stored in JIT_GLOBAL_SYMBOL_NAMES.

  Must contain JIT_GLOBAL_SYMBOL_COUNT entries.

  Option type: void **. Applies to: dynamic linker only

• JIT_GLOBAL_SYMBOL_COUNT - Number of entries in JIT_GLOBAL_SYMBOL_NAMES and JIT_GLOBAL_SYMBOL_ADDRESSES arrays.

  Option type: unsigned int. Applies to: dynamic linker only

• JIT_LTO - Enable link-time optimization (-dlto) for device code (0: false, default)

  Option type: int. Applies to: compiler and linker

• JIT_FTZ - Control single-precision denormals (-ftz) support (0: false, default).
  • 1 : flushes denormal values to zero
  • 0 : preserves denormal values

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_PREC_DIV - Control single-precision floating-point division and reciprocals (-prec-div) support (1: true, default).
  • 1 : Enables the IEEE round-to-nearest mode
  • 0 : Enables the fast approximation mode

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_PREC_SQRT - Control single-precision floating-point square root (-prec-sqrt) support (1: true, default).
  • 1 : Enables the IEEE round-to-nearest mode
  • 0 : Enables the fast approximation mode

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_FMA - Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_NUM_OPTIONS - Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

See Also:

• Constant Field Values

CU_JIT_PREC_DIV

public static final int CU_JIT_PREC_DIV

Online compiler and linker options. (CUjit_option)

Enum values:

• JIT_MAX_REGISTERS - Max number of registers that a thread may use.

  Option type: unsigned int. Applies to: compiler only

• JIT_THREADS_PER_BLOCK - IN: Specifies minimum number of threads per block to target compilation for

  OUT: Returns the number of threads the compiler actually targeted.

  This restricts the resource utilization fo the compiler (e.g. max registers) such that a block with the given number of threads should be able to launch based on register limitations. Note, this option does not currently take into account any other resource limitations, such as shared memory utilization.

  Cannot be combined with JIT_TARGET. Option type: unsigned int. Applies to: compiler only

• JIT_WALL_TIME - Overwrites the option value with the total wall clock time, in milliseconds, spent in the compiler and linker.

  Option type: float. Applies to: compiler and linker

• JIT_INFO_LOG_BUFFER - Pointer to a buffer in which to print any log messages that are informational in nature (the buffer size is specified via option JIT_INFO_LOG_BUFFER_SIZE_BYTES).

  Option type: char *. Applies to: compiler and linker

• JIT_INFO_LOG_BUFFER_SIZE_BYTES - IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).

  OUT: Amount of log buffer filled with messages.

  Option type: unsigned int. Applies to: compiler and linker

• JIT_ERROR_LOG_BUFFER - Pointer to a buffer in which to print any log messages that reflect errors (the buffer size is specified via option JIT_ERROR_LOG_BUFFER_SIZE_BYTES).

  Option type: char *. Applies to: compiler and linker

• JIT_ERROR_LOG_BUFFER_SIZE_BYTES - IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).

  OUT: Amount of log buffer filled with messages.

  Option type: unsigned int. Applies to: compiler and linker

• JIT_OPTIMIZATION_LEVEL - Level of optimizations to apply to generated code (0 - 4), with 4 being the default and highest level of optimizations.

  Option type: unsigned int. Applies to: compiler only

• JIT_TARGET_FROM_CUCONTEXT - No option value required. Determines the target based on the current attached context (default).

  Option type: No option value needed. Applies to: compiler and linker

• JIT_TARGET - Target is chosen based on supplied CUjit_target. Cannot be combined with JIT_THREADS_PER_BLOCK.

  Option type: unsigned int for enumerated type CUjit_target. Applies to: compiler and linker

• JIT_FALLBACK_STRATEGY - Specifies choice of fallback strategy if matching cubin is not found.

  Choice is based on supplied CUjit_fallback. This option cannot be used with cuLink* APIs as the linker requires exact matches.

  Option type: unsigned int for enumerated type CUjit_fallback. Applies to: compiler only

• JIT_GENERATE_DEBUG_INFO - Specifies whether to create debug information in output (-g) (0: false, default).

  Option type: int. Applies to: compiler and linker

• JIT_LOG_VERBOSE - Generate verbose log messages (0: false, default).

  Option type: int. Applies to: compiler and linker

• JIT_GENERATE_LINE_INFO - Generate line number information (-lineinfo) (0: false, default).

  Option type: int. Applies to: compiler only

• JIT_CACHE_MODE - Specifies whether to enable caching explicitly (-dlcm). Choice is based on supplied CUjit_cacheMode_enum.

  Option type: unsigned int for enumerated type CUjit_cacheMode_enum. Applies to: compiler only

• JIT_NEW_SM3X_OPT - Used for internal purposes only, in this version of CUDA.
• JIT_FAST_COMPILE - Used for internal purposes only, in this version of CUDA.
• JIT_GLOBAL_SYMBOL_NAMES - Array of device symbol names that will be relocated to the corresponing host addresses stored in JIT_GLOBAL_SYMBOL_ADDRESSES.

  Must contain JIT_GLOBAL_SYMBOL_COUNT entries. When loding a device module, driver will relocate all encountered unresolved symbols to the host addresses. It is only allowed to register symbols that correspond to unresolved global variables. It is illegal to register the same device symbol at multiple addresses.

  Option type: const char **. Applies to: dynamic linker only

• JIT_GLOBAL_SYMBOL_ADDRESSES - Array of host addresses that will be used to relocate corresponding device symbols stored in JIT_GLOBAL_SYMBOL_NAMES.

  Must contain JIT_GLOBAL_SYMBOL_COUNT entries.

  Option type: void **. Applies to: dynamic linker only

• JIT_GLOBAL_SYMBOL_COUNT - Number of entries in JIT_GLOBAL_SYMBOL_NAMES and JIT_GLOBAL_SYMBOL_ADDRESSES arrays.

  Option type: unsigned int. Applies to: dynamic linker only

• JIT_LTO - Enable link-time optimization (-dlto) for device code (0: false, default)

  Option type: int. Applies to: compiler and linker

• JIT_FTZ - Control single-precision denormals (-ftz) support (0: false, default).
  • 1 : flushes denormal values to zero
  • 0 : preserves denormal values

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_PREC_DIV - Control single-precision floating-point division and reciprocals (-prec-div) support (1: true, default).
  • 1 : Enables the IEEE round-to-nearest mode
  • 0 : Enables the fast approximation mode

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_PREC_SQRT - Control single-precision floating-point square root (-prec-sqrt) support (1: true, default).
  • 1 : Enables the IEEE round-to-nearest mode
  • 0 : Enables the fast approximation mode

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_FMA - Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_NUM_OPTIONS - Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

See Also:

• Constant Field Values

CU_JIT_PREC_SQRT

public static final int CU_JIT_PREC_SQRT

Online compiler and linker options. (CUjit_option)

Enum values:

• JIT_MAX_REGISTERS - Max number of registers that a thread may use.

  Option type: unsigned int. Applies to: compiler only

• JIT_THREADS_PER_BLOCK - IN: Specifies minimum number of threads per block to target compilation for

  OUT: Returns the number of threads the compiler actually targeted.

  This restricts the resource utilization fo the compiler (e.g. max registers) such that a block with the given number of threads should be able to launch based on register limitations. Note, this option does not currently take into account any other resource limitations, such as shared memory utilization.

  Cannot be combined with JIT_TARGET. Option type: unsigned int. Applies to: compiler only

• JIT_WALL_TIME - Overwrites the option value with the total wall clock time, in milliseconds, spent in the compiler and linker.

  Option type: float. Applies to: compiler and linker

• JIT_INFO_LOG_BUFFER - Pointer to a buffer in which to print any log messages that are informational in nature (the buffer size is specified via option JIT_INFO_LOG_BUFFER_SIZE_BYTES).

  Option type: char *. Applies to: compiler and linker

• JIT_INFO_LOG_BUFFER_SIZE_BYTES - IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).

  OUT: Amount of log buffer filled with messages.

  Option type: unsigned int. Applies to: compiler and linker

• JIT_ERROR_LOG_BUFFER - Pointer to a buffer in which to print any log messages that reflect errors (the buffer size is specified via option JIT_ERROR_LOG_BUFFER_SIZE_BYTES).

  Option type: char *. Applies to: compiler and linker

• JIT_ERROR_LOG_BUFFER_SIZE_BYTES - IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).

  OUT: Amount of log buffer filled with messages.

  Option type: unsigned int. Applies to: compiler and linker

• JIT_OPTIMIZATION_LEVEL - Level of optimizations to apply to generated code (0 - 4), with 4 being the default and highest level of optimizations.

  Option type: unsigned int. Applies to: compiler only

• JIT_TARGET_FROM_CUCONTEXT - No option value required. Determines the target based on the current attached context (default).

  Option type: No option value needed. Applies to: compiler and linker

• JIT_TARGET - Target is chosen based on supplied CUjit_target. Cannot be combined with JIT_THREADS_PER_BLOCK.

  Option type: unsigned int for enumerated type CUjit_target. Applies to: compiler and linker

• JIT_FALLBACK_STRATEGY - Specifies choice of fallback strategy if matching cubin is not found.

  Choice is based on supplied CUjit_fallback. This option cannot be used with cuLink* APIs as the linker requires exact matches.

  Option type: unsigned int for enumerated type CUjit_fallback. Applies to: compiler only

• JIT_GENERATE_DEBUG_INFO - Specifies whether to create debug information in output (-g) (0: false, default).

  Option type: int. Applies to: compiler and linker

• JIT_LOG_VERBOSE - Generate verbose log messages (0: false, default).

  Option type: int. Applies to: compiler and linker

• JIT_GENERATE_LINE_INFO - Generate line number information (-lineinfo) (0: false, default).

  Option type: int. Applies to: compiler only

• JIT_CACHE_MODE - Specifies whether to enable caching explicitly (-dlcm). Choice is based on supplied CUjit_cacheMode_enum.

  Option type: unsigned int for enumerated type CUjit_cacheMode_enum. Applies to: compiler only

• JIT_NEW_SM3X_OPT - Used for internal purposes only, in this version of CUDA.
• JIT_FAST_COMPILE - Used for internal purposes only, in this version of CUDA.
• JIT_GLOBAL_SYMBOL_NAMES - Array of device symbol names that will be relocated to the corresponing host addresses stored in JIT_GLOBAL_SYMBOL_ADDRESSES.

  Must contain JIT_GLOBAL_SYMBOL_COUNT entries. When loding a device module, driver will relocate all encountered unresolved symbols to the host addresses. It is only allowed to register symbols that correspond to unresolved global variables. It is illegal to register the same device symbol at multiple addresses.

  Option type: const char **. Applies to: dynamic linker only

• JIT_GLOBAL_SYMBOL_ADDRESSES - Array of host addresses that will be used to relocate corresponding device symbols stored in JIT_GLOBAL_SYMBOL_NAMES.

  Must contain JIT_GLOBAL_SYMBOL_COUNT entries.

  Option type: void **. Applies to: dynamic linker only

• JIT_GLOBAL_SYMBOL_COUNT - Number of entries in JIT_GLOBAL_SYMBOL_NAMES and JIT_GLOBAL_SYMBOL_ADDRESSES arrays.

  Option type: unsigned int. Applies to: dynamic linker only

• JIT_LTO - Enable link-time optimization (-dlto) for device code (0: false, default)

  Option type: int. Applies to: compiler and linker

• JIT_FTZ - Control single-precision denormals (-ftz) support (0: false, default).
  • 1 : flushes denormal values to zero
  • 0 : preserves denormal values

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_PREC_DIV - Control single-precision floating-point division and reciprocals (-prec-div) support (1: true, default).
  • 1 : Enables the IEEE round-to-nearest mode
  • 0 : Enables the fast approximation mode

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_PREC_SQRT - Control single-precision floating-point square root (-prec-sqrt) support (1: true, default).
  • 1 : Enables the IEEE round-to-nearest mode
  • 0 : Enables the fast approximation mode

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_FMA - Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_NUM_OPTIONS - Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

See Also:

• Constant Field Values

CU_JIT_FMA

public static final int CU_JIT_FMA

Online compiler and linker options. (CUjit_option)

Enum values:

• JIT_MAX_REGISTERS - Max number of registers that a thread may use.

  Option type: unsigned int. Applies to: compiler only

• JIT_THREADS_PER_BLOCK - IN: Specifies minimum number of threads per block to target compilation for

  OUT: Returns the number of threads the compiler actually targeted.

  This restricts the resource utilization fo the compiler (e.g. max registers) such that a block with the given number of threads should be able to launch based on register limitations. Note, this option does not currently take into account any other resource limitations, such as shared memory utilization.

  Cannot be combined with JIT_TARGET. Option type: unsigned int. Applies to: compiler only

• JIT_WALL_TIME - Overwrites the option value with the total wall clock time, in milliseconds, spent in the compiler and linker.

  Option type: float. Applies to: compiler and linker

• JIT_INFO_LOG_BUFFER - Pointer to a buffer in which to print any log messages that are informational in nature (the buffer size is specified via option JIT_INFO_LOG_BUFFER_SIZE_BYTES).

  Option type: char *. Applies to: compiler and linker

• JIT_INFO_LOG_BUFFER_SIZE_BYTES - IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).

  OUT: Amount of log buffer filled with messages.

  Option type: unsigned int. Applies to: compiler and linker

• JIT_ERROR_LOG_BUFFER - Pointer to a buffer in which to print any log messages that reflect errors (the buffer size is specified via option JIT_ERROR_LOG_BUFFER_SIZE_BYTES).

  Option type: char *. Applies to: compiler and linker

• JIT_ERROR_LOG_BUFFER_SIZE_BYTES - IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).

  OUT: Amount of log buffer filled with messages.

  Option type: unsigned int. Applies to: compiler and linker

• JIT_OPTIMIZATION_LEVEL - Level of optimizations to apply to generated code (0 - 4), with 4 being the default and highest level of optimizations.

  Option type: unsigned int. Applies to: compiler only

• JIT_TARGET_FROM_CUCONTEXT - No option value required. Determines the target based on the current attached context (default).

  Option type: No option value needed. Applies to: compiler and linker

• JIT_TARGET - Target is chosen based on supplied CUjit_target. Cannot be combined with JIT_THREADS_PER_BLOCK.

  Option type: unsigned int for enumerated type CUjit_target. Applies to: compiler and linker

• JIT_FALLBACK_STRATEGY - Specifies choice of fallback strategy if matching cubin is not found.

  Choice is based on supplied CUjit_fallback. This option cannot be used with cuLink* APIs as the linker requires exact matches.

  Option type: unsigned int for enumerated type CUjit_fallback. Applies to: compiler only

• JIT_GENERATE_DEBUG_INFO - Specifies whether to create debug information in output (-g) (0: false, default).

  Option type: int. Applies to: compiler and linker

• JIT_LOG_VERBOSE - Generate verbose log messages (0: false, default).

  Option type: int. Applies to: compiler and linker

• JIT_GENERATE_LINE_INFO - Generate line number information (-lineinfo) (0: false, default).

  Option type: int. Applies to: compiler only

• JIT_CACHE_MODE - Specifies whether to enable caching explicitly (-dlcm). Choice is based on supplied CUjit_cacheMode_enum.

  Option type: unsigned int for enumerated type CUjit_cacheMode_enum. Applies to: compiler only

• JIT_NEW_SM3X_OPT - Used for internal purposes only, in this version of CUDA.
• JIT_FAST_COMPILE - Used for internal purposes only, in this version of CUDA.
• JIT_GLOBAL_SYMBOL_NAMES - Array of device symbol names that will be relocated to the corresponing host addresses stored in JIT_GLOBAL_SYMBOL_ADDRESSES.

  Must contain JIT_GLOBAL_SYMBOL_COUNT entries. When loding a device module, driver will relocate all encountered unresolved symbols to the host addresses. It is only allowed to register symbols that correspond to unresolved global variables. It is illegal to register the same device symbol at multiple addresses.

  Option type: const char **. Applies to: dynamic linker only

• JIT_GLOBAL_SYMBOL_ADDRESSES - Array of host addresses that will be used to relocate corresponding device symbols stored in JIT_GLOBAL_SYMBOL_NAMES.

  Must contain JIT_GLOBAL_SYMBOL_COUNT entries.

  Option type: void **. Applies to: dynamic linker only

• JIT_GLOBAL_SYMBOL_COUNT - Number of entries in JIT_GLOBAL_SYMBOL_NAMES and JIT_GLOBAL_SYMBOL_ADDRESSES arrays.

  Option type: unsigned int. Applies to: dynamic linker only

• JIT_LTO - Enable link-time optimization (-dlto) for device code (0: false, default)

  Option type: int. Applies to: compiler and linker

• JIT_FTZ - Control single-precision denormals (-ftz) support (0: false, default).
  • 1 : flushes denormal values to zero
  • 0 : preserves denormal values

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_PREC_DIV - Control single-precision floating-point division and reciprocals (-prec-div) support (1: true, default).
  • 1 : Enables the IEEE round-to-nearest mode
  • 0 : Enables the fast approximation mode

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_PREC_SQRT - Control single-precision floating-point square root (-prec-sqrt) support (1: true, default).
  • 1 : Enables the IEEE round-to-nearest mode
  • 0 : Enables the fast approximation mode

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_FMA - Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_NUM_OPTIONS - Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

See Also:

• Constant Field Values

CU_JIT_NUM_OPTIONS

public static final int CU_JIT_NUM_OPTIONS

Online compiler and linker options. (CUjit_option)

Enum values:

• JIT_MAX_REGISTERS - Max number of registers that a thread may use.

  Option type: unsigned int. Applies to: compiler only

• JIT_THREADS_PER_BLOCK - IN: Specifies minimum number of threads per block to target compilation for

  OUT: Returns the number of threads the compiler actually targeted.

  This restricts the resource utilization fo the compiler (e.g. max registers) such that a block with the given number of threads should be able to launch based on register limitations. Note, this option does not currently take into account any other resource limitations, such as shared memory utilization.

  Cannot be combined with JIT_TARGET. Option type: unsigned int. Applies to: compiler only

• JIT_WALL_TIME - Overwrites the option value with the total wall clock time, in milliseconds, spent in the compiler and linker.

  Option type: float. Applies to: compiler and linker

• JIT_INFO_LOG_BUFFER - Pointer to a buffer in which to print any log messages that are informational in nature (the buffer size is specified via option JIT_INFO_LOG_BUFFER_SIZE_BYTES).

  Option type: char *. Applies to: compiler and linker

• JIT_INFO_LOG_BUFFER_SIZE_BYTES - IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).

  OUT: Amount of log buffer filled with messages.

  Option type: unsigned int. Applies to: compiler and linker

• JIT_ERROR_LOG_BUFFER - Pointer to a buffer in which to print any log messages that reflect errors (the buffer size is specified via option JIT_ERROR_LOG_BUFFER_SIZE_BYTES).

  Option type: char *. Applies to: compiler and linker

• JIT_ERROR_LOG_BUFFER_SIZE_BYTES - IN: Log buffer size in bytes. Log messages will be capped at this size (including null terminator).

  OUT: Amount of log buffer filled with messages.

  Option type: unsigned int. Applies to: compiler and linker

• JIT_OPTIMIZATION_LEVEL - Level of optimizations to apply to generated code (0 - 4), with 4 being the default and highest level of optimizations.

  Option type: unsigned int. Applies to: compiler only

• JIT_TARGET_FROM_CUCONTEXT - No option value required. Determines the target based on the current attached context (default).

  Option type: No option value needed. Applies to: compiler and linker

• JIT_TARGET - Target is chosen based on supplied CUjit_target. Cannot be combined with JIT_THREADS_PER_BLOCK.

  Option type: unsigned int for enumerated type CUjit_target. Applies to: compiler and linker

• JIT_FALLBACK_STRATEGY - Specifies choice of fallback strategy if matching cubin is not found.

  Choice is based on supplied CUjit_fallback. This option cannot be used with cuLink* APIs as the linker requires exact matches.

  Option type: unsigned int for enumerated type CUjit_fallback. Applies to: compiler only

• JIT_GENERATE_DEBUG_INFO - Specifies whether to create debug information in output (-g) (0: false, default).

  Option type: int. Applies to: compiler and linker

• JIT_LOG_VERBOSE - Generate verbose log messages (0: false, default).

  Option type: int. Applies to: compiler and linker

• JIT_GENERATE_LINE_INFO - Generate line number information (-lineinfo) (0: false, default).

  Option type: int. Applies to: compiler only

• JIT_CACHE_MODE - Specifies whether to enable caching explicitly (-dlcm). Choice is based on supplied CUjit_cacheMode_enum.

  Option type: unsigned int for enumerated type CUjit_cacheMode_enum. Applies to: compiler only

• JIT_NEW_SM3X_OPT - Used for internal purposes only, in this version of CUDA.
• JIT_FAST_COMPILE - Used for internal purposes only, in this version of CUDA.
• JIT_GLOBAL_SYMBOL_NAMES - Array of device symbol names that will be relocated to the corresponing host addresses stored in JIT_GLOBAL_SYMBOL_ADDRESSES.

  Must contain JIT_GLOBAL_SYMBOL_COUNT entries. When loding a device module, driver will relocate all encountered unresolved symbols to the host addresses. It is only allowed to register symbols that correspond to unresolved global variables. It is illegal to register the same device symbol at multiple addresses.

  Option type: const char **. Applies to: dynamic linker only

• JIT_GLOBAL_SYMBOL_ADDRESSES - Array of host addresses that will be used to relocate corresponding device symbols stored in JIT_GLOBAL_SYMBOL_NAMES.

  Must contain JIT_GLOBAL_SYMBOL_COUNT entries.

  Option type: void **. Applies to: dynamic linker only

• JIT_GLOBAL_SYMBOL_COUNT - Number of entries in JIT_GLOBAL_SYMBOL_NAMES and JIT_GLOBAL_SYMBOL_ADDRESSES arrays.

  Option type: unsigned int. Applies to: dynamic linker only

• JIT_LTO - Enable link-time optimization (-dlto) for device code (0: false, default)

  Option type: int. Applies to: compiler and linker

• JIT_FTZ - Control single-precision denormals (-ftz) support (0: false, default).
  • 1 : flushes denormal values to zero
  • 0 : preserves denormal values

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_PREC_DIV - Control single-precision floating-point division and reciprocals (-prec-div) support (1: true, default).
  • 1 : Enables the IEEE round-to-nearest mode
  • 0 : Enables the fast approximation mode

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_PREC_SQRT - Control single-precision floating-point square root (-prec-sqrt) support (1: true, default).
  • 1 : Enables the IEEE round-to-nearest mode
  • 0 : Enables the fast approximation mode

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_FMA - Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

• JIT_NUM_OPTIONS - Enable/Disable the contraction of floating-point multiplies and adds/subtracts into floating-point multiply-add (-fma) operations (1: Enable, default; 0: Disable).

  Option type: int. Applies to: link-time optimization specified with JIT_LTO

See Also:

• Constant Field Values

CU_TARGET_COMPUTE_20

public static final int CU_TARGET_COMPUTE_20

Online compilation targets. (CUjit_target)

Enum values:

• TARGET_COMPUTE_20 - Compute device class 2.0
• TARGET_COMPUTE_21 - Compute device class 2.1
• TARGET_COMPUTE_30 - Compute device class 3.0
• TARGET_COMPUTE_32 - Compute device class 3.2
• TARGET_COMPUTE_35 - Compute device class 3.5
• TARGET_COMPUTE_37 - Compute device class 3.7
• TARGET_COMPUTE_50 - Compute device class 5.0
• TARGET_COMPUTE_52 - Compute device class 5.2
• TARGET_COMPUTE_53 - Compute device class 5.3
• TARGET_COMPUTE_60 - Compute device class 6.0.
• TARGET_COMPUTE_61 - Compute device class 6.1.
• TARGET_COMPUTE_62 - Compute device class 6.2.
• TARGET_COMPUTE_70 - Compute device class 7.0.
• TARGET_COMPUTE_72 - Compute device class 7.2.
• TARGET_COMPUTE_75 - Compute device class 7.5.
• TARGET_COMPUTE_80 - Compute device class 8.0.
• TARGET_COMPUTE_86 - Compute device class 8.6.

See Also:

• Constant Field Values

CU_TARGET_COMPUTE_21

public static final int CU_TARGET_COMPUTE_21

Online compilation targets. (CUjit_target)

Enum values:

• TARGET_COMPUTE_20 - Compute device class 2.0
• TARGET_COMPUTE_21 - Compute device class 2.1
• TARGET_COMPUTE_30 - Compute device class 3.0
• TARGET_COMPUTE_32 - Compute device class 3.2
• TARGET_COMPUTE_35 - Compute device class 3.5
• TARGET_COMPUTE_37 - Compute device class 3.7
• TARGET_COMPUTE_50 - Compute device class 5.0
• TARGET_COMPUTE_52 - Compute device class 5.2
• TARGET_COMPUTE_53 - Compute device class 5.3
• TARGET_COMPUTE_60 - Compute device class 6.0.
• TARGET_COMPUTE_61 - Compute device class 6.1.
• TARGET_COMPUTE_62 - Compute device class 6.2.
• TARGET_COMPUTE_70 - Compute device class 7.0.
• TARGET_COMPUTE_72 - Compute device class 7.2.
• TARGET_COMPUTE_75 - Compute device class 7.5.
• TARGET_COMPUTE_80 - Compute device class 8.0.
• TARGET_COMPUTE_86 - Compute device class 8.6.

See Also:

• Constant Field Values

CU_TARGET_COMPUTE_30

public static final int CU_TARGET_COMPUTE_30

Online compilation targets. (CUjit_target)

Enum values:

• TARGET_COMPUTE_20 - Compute device class 2.0
• TARGET_COMPUTE_21 - Compute device class 2.1
• TARGET_COMPUTE_30 - Compute device class 3.0
• TARGET_COMPUTE_32 - Compute device class 3.2
• TARGET_COMPUTE_35 - Compute device class 3.5
• TARGET_COMPUTE_37 - Compute device class 3.7
• TARGET_COMPUTE_50 - Compute device class 5.0
• TARGET_COMPUTE_52 - Compute device class 5.2
• TARGET_COMPUTE_53 - Compute device class 5.3
• TARGET_COMPUTE_60 - Compute device class 6.0.
• TARGET_COMPUTE_61 - Compute device class 6.1.
• TARGET_COMPUTE_62 - Compute device class 6.2.
• TARGET_COMPUTE_70 - Compute device class 7.0.
• TARGET_COMPUTE_72 - Compute device class 7.2.
• TARGET_COMPUTE_75 - Compute device class 7.5.
• TARGET_COMPUTE_80 - Compute device class 8.0.
• TARGET_COMPUTE_86 - Compute device class 8.6.

See Also:

• Constant Field Values

CU_TARGET_COMPUTE_32

public static final int CU_TARGET_COMPUTE_32

Online compilation targets. (CUjit_target)

Enum values:

• TARGET_COMPUTE_20 - Compute device class 2.0
• TARGET_COMPUTE_21 - Compute device class 2.1
• TARGET_COMPUTE_30 - Compute device class 3.0
• TARGET_COMPUTE_32 - Compute device class 3.2
• TARGET_COMPUTE_35 - Compute device class 3.5
• TARGET_COMPUTE_37 - Compute device class 3.7
• TARGET_COMPUTE_50 - Compute device class 5.0
• TARGET_COMPUTE_52 - Compute device class 5.2
• TARGET_COMPUTE_53 - Compute device class 5.3
• TARGET_COMPUTE_60 - Compute device class 6.0.
• TARGET_COMPUTE_61 - Compute device class 6.1.
• TARGET_COMPUTE_62 - Compute device class 6.2.
• TARGET_COMPUTE_70 - Compute device class 7.0.
• TARGET_COMPUTE_72 - Compute device class 7.2.
• TARGET_COMPUTE_75 - Compute device class 7.5.
• TARGET_COMPUTE_80 - Compute device class 8.0.
• TARGET_COMPUTE_86 - Compute device class 8.6.

See Also:

• Constant Field Values

CU_TARGET_COMPUTE_35

public static final int CU_TARGET_COMPUTE_35

Online compilation targets. (CUjit_target)

Enum values:

• TARGET_COMPUTE_20 - Compute device class 2.0
• TARGET_COMPUTE_21 - Compute device class 2.1
• TARGET_COMPUTE_30 - Compute device class 3.0
• TARGET_COMPUTE_32 - Compute device class 3.2
• TARGET_COMPUTE_35 - Compute device class 3.5
• TARGET_COMPUTE_37 - Compute device class 3.7
• TARGET_COMPUTE_50 - Compute device class 5.0
• TARGET_COMPUTE_52 - Compute device class 5.2
• TARGET_COMPUTE_53 - Compute device class 5.3
• TARGET_COMPUTE_60 - Compute device class 6.0.
• TARGET_COMPUTE_61 - Compute device class 6.1.
• TARGET_COMPUTE_62 - Compute device class 6.2.
• TARGET_COMPUTE_70 - Compute device class 7.0.
• TARGET_COMPUTE_72 - Compute device class 7.2.
• TARGET_COMPUTE_75 - Compute device class 7.5.
• TARGET_COMPUTE_80 - Compute device class 8.0.
• TARGET_COMPUTE_86 - Compute device class 8.6.

See Also:

• Constant Field Values

CU_TARGET_COMPUTE_37

public static final int CU_TARGET_COMPUTE_37

Online compilation targets. (CUjit_target)

Enum values:

• TARGET_COMPUTE_20 - Compute device class 2.0
• TARGET_COMPUTE_21 - Compute device class 2.1
• TARGET_COMPUTE_30 - Compute device class 3.0
• TARGET_COMPUTE_32 - Compute device class 3.2
• TARGET_COMPUTE_35 - Compute device class 3.5
• TARGET_COMPUTE_37 - Compute device class 3.7
• TARGET_COMPUTE_50 - Compute device class 5.0
• TARGET_COMPUTE_52 - Compute device class 5.2
• TARGET_COMPUTE_53 - Compute device class 5.3
• TARGET_COMPUTE_60 - Compute device class 6.0.
• TARGET_COMPUTE_61 - Compute device class 6.1.
• TARGET_COMPUTE_62 - Compute device class 6.2.
• TARGET_COMPUTE_70 - Compute device class 7.0.
• TARGET_COMPUTE_72 - Compute device class 7.2.
• TARGET_COMPUTE_75 - Compute device class 7.5.
• TARGET_COMPUTE_80 - Compute device class 8.0.
• TARGET_COMPUTE_86 - Compute device class 8.6.

See Also:

• Constant Field Values

CU_TARGET_COMPUTE_50

public static final int CU_TARGET_COMPUTE_50

Online compilation targets. (CUjit_target)

Enum values:

• TARGET_COMPUTE_20 - Compute device class 2.0
• TARGET_COMPUTE_21 - Compute device class 2.1
• TARGET_COMPUTE_30 - Compute device class 3.0
• TARGET_COMPUTE_32 - Compute device class 3.2
• TARGET_COMPUTE_35 - Compute device class 3.5
• TARGET_COMPUTE_37 - Compute device class 3.7
• TARGET_COMPUTE_50 - Compute device class 5.0
• TARGET_COMPUTE_52 - Compute device class 5.2
• TARGET_COMPUTE_53 - Compute device class 5.3
• TARGET_COMPUTE_60 - Compute device class 6.0.
• TARGET_COMPUTE_61 - Compute device class 6.1.
• TARGET_COMPUTE_62 - Compute device class 6.2.
• TARGET_COMPUTE_70 - Compute device class 7.0.
• TARGET_COMPUTE_72 - Compute device class 7.2.
• TARGET_COMPUTE_75 - Compute device class 7.5.
• TARGET_COMPUTE_80 - Compute device class 8.0.
• TARGET_COMPUTE_86 - Compute device class 8.6.

See Also:

• Constant Field Values

CU_TARGET_COMPUTE_52

public static final int CU_TARGET_COMPUTE_52

Online compilation targets. (CUjit_target)

Enum values:

• TARGET_COMPUTE_20 - Compute device class 2.0
• TARGET_COMPUTE_21 - Compute device class 2.1
• TARGET_COMPUTE_30 - Compute device class 3.0
• TARGET_COMPUTE_32 - Compute device class 3.2
• TARGET_COMPUTE_35 - Compute device class 3.5
• TARGET_COMPUTE_37 - Compute device class 3.7
• TARGET_COMPUTE_50 - Compute device class 5.0
• TARGET_COMPUTE_52 - Compute device class 5.2
• TARGET_COMPUTE_53 - Compute device class 5.3
• TARGET_COMPUTE_60 - Compute device class 6.0.
• TARGET_COMPUTE_61 - Compute device class 6.1.
• TARGET_COMPUTE_62 - Compute device class 6.2.
• TARGET_COMPUTE_70 - Compute device class 7.0.
• TARGET_COMPUTE_72 - Compute device class 7.2.
• TARGET_COMPUTE_75 - Compute device class 7.5.
• TARGET_COMPUTE_80 - Compute device class 8.0.
• TARGET_COMPUTE_86 - Compute device class 8.6.

See Also:

• Constant Field Values

CU_TARGET_COMPUTE_53

public static final int CU_TARGET_COMPUTE_53

Online compilation targets. (CUjit_target)

Enum values:

• TARGET_COMPUTE_20 - Compute device class 2.0
• TARGET_COMPUTE_21 - Compute device class 2.1
• TARGET_COMPUTE_30 - Compute device class 3.0
• TARGET_COMPUTE_32 - Compute device class 3.2
• TARGET_COMPUTE_35 - Compute device class 3.5
• TARGET_COMPUTE_37 - Compute device class 3.7
• TARGET_COMPUTE_50 - Compute device class 5.0
• TARGET_COMPUTE_52 - Compute device class 5.2
• TARGET_COMPUTE_53 - Compute device class 5.3
• TARGET_COMPUTE_60 - Compute device class 6.0.
• TARGET_COMPUTE_61 - Compute device class 6.1.
• TARGET_COMPUTE_62 - Compute device class 6.2.
• TARGET_COMPUTE_70 - Compute device class 7.0.
• TARGET_COMPUTE_72 - Compute device class 7.2.
• TARGET_COMPUTE_75 - Compute device class 7.5.
• TARGET_COMPUTE_80 - Compute device class 8.0.
• TARGET_COMPUTE_86 - Compute device class 8.6.

See Also:

• Constant Field Values

CU_TARGET_COMPUTE_60

public static final int CU_TARGET_COMPUTE_60

Online compilation targets. (CUjit_target)

Enum values:

• TARGET_COMPUTE_20 - Compute device class 2.0
• TARGET_COMPUTE_21 - Compute device class 2.1
• TARGET_COMPUTE_30 - Compute device class 3.0
• TARGET_COMPUTE_32 - Compute device class 3.2
• TARGET_COMPUTE_35 - Compute device class 3.5
• TARGET_COMPUTE_37 - Compute device class 3.7
• TARGET_COMPUTE_50 - Compute device class 5.0
• TARGET_COMPUTE_52 - Compute device class 5.2
• TARGET_COMPUTE_53 - Compute device class 5.3
• TARGET_COMPUTE_60 - Compute device class 6.0.
• TARGET_COMPUTE_61 - Compute device class 6.1.
• TARGET_COMPUTE_62 - Compute device class 6.2.
• TARGET_COMPUTE_70 - Compute device class 7.0.
• TARGET_COMPUTE_72 - Compute device class 7.2.
• TARGET_COMPUTE_75 - Compute device class 7.5.
• TARGET_COMPUTE_80 - Compute device class 8.0.
• TARGET_COMPUTE_86 - Compute device class 8.6.

See Also:

• Constant Field Values

CU_TARGET_COMPUTE_61

public static final int CU_TARGET_COMPUTE_61

Online compilation targets. (CUjit_target)

Enum values:

• TARGET_COMPUTE_20 - Compute device class 2.0
• TARGET_COMPUTE_21 - Compute device class 2.1
• TARGET_COMPUTE_30 - Compute device class 3.0
• TARGET_COMPUTE_32 - Compute device class 3.2
• TARGET_COMPUTE_35 - Compute device class 3.5
• TARGET_COMPUTE_37 - Compute device class 3.7
• TARGET_COMPUTE_50 - Compute device class 5.0
• TARGET_COMPUTE_52 - Compute device class 5.2
• TARGET_COMPUTE_53 - Compute device class 5.3
• TARGET_COMPUTE_60 - Compute device class 6.0.
• TARGET_COMPUTE_61 - Compute device class 6.1.
• TARGET_COMPUTE_62 - Compute device class 6.2.
• TARGET_COMPUTE_70 - Compute device class 7.0.
• TARGET_COMPUTE_72 - Compute device class 7.2.
• TARGET_COMPUTE_75 - Compute device class 7.5.
• TARGET_COMPUTE_80 - Compute device class 8.0.
• TARGET_COMPUTE_86 - Compute device class 8.6.

See Also:

• Constant Field Values

CU_TARGET_COMPUTE_62

public static final int CU_TARGET_COMPUTE_62

Online compilation targets. (CUjit_target)

Enum values:

• TARGET_COMPUTE_20 - Compute device class 2.0
• TARGET_COMPUTE_21 - Compute device class 2.1
• TARGET_COMPUTE_30 - Compute device class 3.0
• TARGET_COMPUTE_32 - Compute device class 3.2
• TARGET_COMPUTE_35 - Compute device class 3.5
• TARGET_COMPUTE_37 - Compute device class 3.7
• TARGET_COMPUTE_50 - Compute device class 5.0
• TARGET_COMPUTE_52 - Compute device class 5.2
• TARGET_COMPUTE_53 - Compute device class 5.3
• TARGET_COMPUTE_60 - Compute device class 6.0.
• TARGET_COMPUTE_61 - Compute device class 6.1.
• TARGET_COMPUTE_62 - Compute device class 6.2.
• TARGET_COMPUTE_70 - Compute device class 7.0.
• TARGET_COMPUTE_72 - Compute device class 7.2.
• TARGET_COMPUTE_75 - Compute device class 7.5.
• TARGET_COMPUTE_80 - Compute device class 8.0.
• TARGET_COMPUTE_86 - Compute device class 8.6.

See Also:

• Constant Field Values

CU_TARGET_COMPUTE_70

public static final int CU_TARGET_COMPUTE_70

Online compilation targets. (CUjit_target)

Enum values:

• TARGET_COMPUTE_20 - Compute device class 2.0
• TARGET_COMPUTE_21 - Compute device class 2.1
• TARGET_COMPUTE_30 - Compute device class 3.0
• TARGET_COMPUTE_32 - Compute device class 3.2
• TARGET_COMPUTE_35 - Compute device class 3.5
• TARGET_COMPUTE_37 - Compute device class 3.7
• TARGET_COMPUTE_50 - Compute device class 5.0
• TARGET_COMPUTE_52 - Compute device class 5.2
• TARGET_COMPUTE_53 - Compute device class 5.3
• TARGET_COMPUTE_60 - Compute device class 6.0.
• TARGET_COMPUTE_61 - Compute device class 6.1.
• TARGET_COMPUTE_62 - Compute device class 6.2.
• TARGET_COMPUTE_70 - Compute device class 7.0.
• TARGET_COMPUTE_72 - Compute device class 7.2.
• TARGET_COMPUTE_75 - Compute device class 7.5.
• TARGET_COMPUTE_80 - Compute device class 8.0.
• TARGET_COMPUTE_86 - Compute device class 8.6.

See Also:

• Constant Field Values

CU_TARGET_COMPUTE_72

public static final int CU_TARGET_COMPUTE_72

Online compilation targets. (CUjit_target)

Enum values:

• TARGET_COMPUTE_20 - Compute device class 2.0
• TARGET_COMPUTE_21 - Compute device class 2.1
• TARGET_COMPUTE_30 - Compute device class 3.0
• TARGET_COMPUTE_32 - Compute device class 3.2
• TARGET_COMPUTE_35 - Compute device class 3.5
• TARGET_COMPUTE_37 - Compute device class 3.7
• TARGET_COMPUTE_50 - Compute device class 5.0
• TARGET_COMPUTE_52 - Compute device class 5.2
• TARGET_COMPUTE_53 - Compute device class 5.3
• TARGET_COMPUTE_60 - Compute device class 6.0.
• TARGET_COMPUTE_61 - Compute device class 6.1.
• TARGET_COMPUTE_62 - Compute device class 6.2.
• TARGET_COMPUTE_70 - Compute device class 7.0.
• TARGET_COMPUTE_72 - Compute device class 7.2.
• TARGET_COMPUTE_75 - Compute device class 7.5.
• TARGET_COMPUTE_80 - Compute device class 8.0.
• TARGET_COMPUTE_86 - Compute device class 8.6.

See Also:

• Constant Field Values

CU_TARGET_COMPUTE_75

public static final int CU_TARGET_COMPUTE_75

Online compilation targets. (CUjit_target)

Enum values:

• TARGET_COMPUTE_20 - Compute device class 2.0
• TARGET_COMPUTE_21 - Compute device class 2.1
• TARGET_COMPUTE_30 - Compute device class 3.0
• TARGET_COMPUTE_32 - Compute device class 3.2
• TARGET_COMPUTE_35 - Compute device class 3.5
• TARGET_COMPUTE_37 - Compute device class 3.7
• TARGET_COMPUTE_50 - Compute device class 5.0
• TARGET_COMPUTE_52 - Compute device class 5.2
• TARGET_COMPUTE_53 - Compute device class 5.3
• TARGET_COMPUTE_60 - Compute device class 6.0.
• TARGET_COMPUTE_61 - Compute device class 6.1.
• TARGET_COMPUTE_62 - Compute device class 6.2.
• TARGET_COMPUTE_70 - Compute device class 7.0.
• TARGET_COMPUTE_72 - Compute device class 7.2.
• TARGET_COMPUTE_75 - Compute device class 7.5.
• TARGET_COMPUTE_80 - Compute device class 8.0.
• TARGET_COMPUTE_86 - Compute device class 8.6.

See Also:

• Constant Field Values

CU_TARGET_COMPUTE_80

public static final int CU_TARGET_COMPUTE_80

Online compilation targets. (CUjit_target)

Enum values:

• TARGET_COMPUTE_20 - Compute device class 2.0
• TARGET_COMPUTE_21 - Compute device class 2.1
• TARGET_COMPUTE_30 - Compute device class 3.0
• TARGET_COMPUTE_32 - Compute device class 3.2
• TARGET_COMPUTE_35 - Compute device class 3.5
• TARGET_COMPUTE_37 - Compute device class 3.7
• TARGET_COMPUTE_50 - Compute device class 5.0
• TARGET_COMPUTE_52 - Compute device class 5.2
• TARGET_COMPUTE_53 - Compute device class 5.3
• TARGET_COMPUTE_60 - Compute device class 6.0.
• TARGET_COMPUTE_61 - Compute device class 6.1.
• TARGET_COMPUTE_62 - Compute device class 6.2.
• TARGET_COMPUTE_70 - Compute device class 7.0.
• TARGET_COMPUTE_72 - Compute device class 7.2.
• TARGET_COMPUTE_75 - Compute device class 7.5.
• TARGET_COMPUTE_80 - Compute device class 8.0.
• TARGET_COMPUTE_86 - Compute device class 8.6.

See Also:

• Constant Field Values

CU_TARGET_COMPUTE_86

public static final int CU_TARGET_COMPUTE_86

Online compilation targets. (CUjit_target)

Enum values:

• TARGET_COMPUTE_20 - Compute device class 2.0
• TARGET_COMPUTE_21 - Compute device class 2.1
• TARGET_COMPUTE_30 - Compute device class 3.0
• TARGET_COMPUTE_32 - Compute device class 3.2
• TARGET_COMPUTE_35 - Compute device class 3.5
• TARGET_COMPUTE_37 - Compute device class 3.7
• TARGET_COMPUTE_50 - Compute device class 5.0
• TARGET_COMPUTE_52 - Compute device class 5.2
• TARGET_COMPUTE_53 - Compute device class 5.3
• TARGET_COMPUTE_60 - Compute device class 6.0.
• TARGET_COMPUTE_61 - Compute device class 6.1.
• TARGET_COMPUTE_62 - Compute device class 6.2.
• TARGET_COMPUTE_70 - Compute device class 7.0.
• TARGET_COMPUTE_72 - Compute device class 7.2.
• TARGET_COMPUTE_75 - Compute device class 7.5.
• TARGET_COMPUTE_80 - Compute device class 8.0.
• TARGET_COMPUTE_86 - Compute device class 8.6.

See Also:

• Constant Field Values

CU_PREFER_PTX

public static final int CU_PREFER_PTX

Cubin matching fallback strategies. (CUjit_fallback)

Enum values:

• PREFER_PTX - Prefer to compile ptx if exact binary match not found
• PREFER_BINARY - Prefer to fall back to compatible binary code if exact match not found

See Also:

• Constant Field Values

CU_PREFER_BINARY

public static final int CU_PREFER_BINARY

Cubin matching fallback strategies. (CUjit_fallback)

Enum values:

• PREFER_PTX - Prefer to compile ptx if exact binary match not found
• PREFER_BINARY - Prefer to fall back to compatible binary code if exact match not found

See Also:

• Constant Field Values

CU_JIT_CACHE_OPTION_NONE

public static final int CU_JIT_CACHE_OPTION_NONE

Caching modes for dlcm. (CUjit_cacheMode)

Enum values:

• JIT_CACHE_OPTION_NONE - Compile with no -dlcm flag specified
• JIT_CACHE_OPTION_CG - Compile with L1 cache disabled
• JIT_CACHE_OPTION_CA - Compile with L1 cache enabled

See Also:

• Constant Field Values

CU_JIT_CACHE_OPTION_CG

public static final int CU_JIT_CACHE_OPTION_CG

Caching modes for dlcm. (CUjit_cacheMode)

Enum values:

• JIT_CACHE_OPTION_NONE - Compile with no -dlcm flag specified
• JIT_CACHE_OPTION_CG - Compile with L1 cache disabled
• JIT_CACHE_OPTION_CA - Compile with L1 cache enabled

See Also:

• Constant Field Values

CU_JIT_CACHE_OPTION_CA

public static final int CU_JIT_CACHE_OPTION_CA

Caching modes for dlcm. (CUjit_cacheMode)

Enum values:

• JIT_CACHE_OPTION_NONE - Compile with no -dlcm flag specified
• JIT_CACHE_OPTION_CG - Compile with L1 cache disabled
• JIT_CACHE_OPTION_CA - Compile with L1 cache enabled

See Also:

• Constant Field Values

CU_JIT_INPUT_CUBIN

public static final int CU_JIT_INPUT_CUBIN

Device code formats. (CUjitInputType)

Enum values:

• JIT_INPUT_CUBIN - Compiled device-class-specific device code

  Applicable options: none

• JIT_INPUT_PTX - PTX source code.

  Applicable options: PTX compiler options

• JIT_INPUT_FATBINARY - Bundle of multiple cubins and/or PTX of some device code.

  Applicable options: PTX compiler options, JIT_FALLBACK_STRATEGY

• JIT_INPUT_OBJECT - Host object with embedded device code.

  Applicable options: PTX compiler options, JIT_FALLBACK_STRATEGY

• JIT_INPUT_LIBRARY - Archive of host objects with embedded device code.

  Applicable options: PTX compiler options, JIT_FALLBACK_STRATEGY

• JIT_INPUT_NVVM - High-level intermediate code for link-time optimization.

  Applicable options: NVVM compiler options, PTX compiler options

See Also:

• Constant Field Values

CU_JIT_INPUT_PTX

public static final int CU_JIT_INPUT_PTX

Device code formats. (CUjitInputType)

Enum values:

• JIT_INPUT_CUBIN - Compiled device-class-specific device code

  Applicable options: none

• JIT_INPUT_PTX - PTX source code.

  Applicable options: PTX compiler options

• JIT_INPUT_FATBINARY - Bundle of multiple cubins and/or PTX of some device code.

  Applicable options: PTX compiler options, JIT_FALLBACK_STRATEGY

• JIT_INPUT_OBJECT - Host object with embedded device code.

  Applicable options: PTX compiler options, JIT_FALLBACK_STRATEGY

• JIT_INPUT_LIBRARY - Archive of host objects with embedded device code.

  Applicable options: PTX compiler options, JIT_FALLBACK_STRATEGY

• JIT_INPUT_NVVM - High-level intermediate code for link-time optimization.

  Applicable options: NVVM compiler options, PTX compiler options

See Also:

• Constant Field Values

CU_JIT_INPUT_FATBINARY

public static final int CU_JIT_INPUT_FATBINARY

Device code formats. (CUjitInputType)

Enum values:

• JIT_INPUT_CUBIN - Compiled device-class-specific device code

  Applicable options: none

• JIT_INPUT_PTX - PTX source code.

  Applicable options: PTX compiler options

• JIT_INPUT_FATBINARY - Bundle of multiple cubins and/or PTX of some device code.

  Applicable options: PTX compiler options, JIT_FALLBACK_STRATEGY

• JIT_INPUT_OBJECT - Host object with embedded device code.

  Applicable options: PTX compiler options, JIT_FALLBACK_STRATEGY

• JIT_INPUT_LIBRARY - Archive of host objects with embedded device code.

  Applicable options: PTX compiler options, JIT_FALLBACK_STRATEGY

• JIT_INPUT_NVVM - High-level intermediate code for link-time optimization.

  Applicable options: NVVM compiler options, PTX compiler options

See Also:

• Constant Field Values

CU_JIT_INPUT_OBJECT

public static final int CU_JIT_INPUT_OBJECT

Device code formats. (CUjitInputType)

Enum values:

• JIT_INPUT_CUBIN - Compiled device-class-specific device code

  Applicable options: none

• JIT_INPUT_PTX - PTX source code.

  Applicable options: PTX compiler options

• JIT_INPUT_FATBINARY - Bundle of multiple cubins and/or PTX of some device code.

  Applicable options: PTX compiler options, JIT_FALLBACK_STRATEGY

• JIT_INPUT_OBJECT - Host object with embedded device code.

  Applicable options: PTX compiler options, JIT_FALLBACK_STRATEGY

• JIT_INPUT_LIBRARY - Archive of host objects with embedded device code.

  Applicable options: PTX compiler options, JIT_FALLBACK_STRATEGY

• JIT_INPUT_NVVM - High-level intermediate code for link-time optimization.

  Applicable options: NVVM compiler options, PTX compiler options

See Also:

• Constant Field Values

CU_JIT_INPUT_LIBRARY

public static final int CU_JIT_INPUT_LIBRARY

Device code formats. (CUjitInputType)

Enum values:

• JIT_INPUT_CUBIN - Compiled device-class-specific device code

  Applicable options: none

• JIT_INPUT_PTX - PTX source code.

  Applicable options: PTX compiler options

• JIT_INPUT_FATBINARY - Bundle of multiple cubins and/or PTX of some device code.

  Applicable options: PTX compiler options, JIT_FALLBACK_STRATEGY

• JIT_INPUT_OBJECT - Host object with embedded device code.

  Applicable options: PTX compiler options, JIT_FALLBACK_STRATEGY

• JIT_INPUT_LIBRARY - Archive of host objects with embedded device code.

  Applicable options: PTX compiler options, JIT_FALLBACK_STRATEGY

• JIT_INPUT_NVVM - High-level intermediate code for link-time optimization.

  Applicable options: NVVM compiler options, PTX compiler options

See Also:

• Constant Field Values

CU_JIT_INPUT_NVVM

public static final int CU_JIT_INPUT_NVVM

Device code formats. (CUjitInputType)

Enum values:

• JIT_INPUT_CUBIN - Compiled device-class-specific device code

  Applicable options: none

• JIT_INPUT_PTX - PTX source code.

  Applicable options: PTX compiler options

• JIT_INPUT_FATBINARY - Bundle of multiple cubins and/or PTX of some device code.

  Applicable options: PTX compiler options, JIT_FALLBACK_STRATEGY

• JIT_INPUT_OBJECT - Host object with embedded device code.

  Applicable options: PTX compiler options, JIT_FALLBACK_STRATEGY

• JIT_INPUT_LIBRARY - Archive of host objects with embedded device code.

  Applicable options: PTX compiler options, JIT_FALLBACK_STRATEGY

• JIT_INPUT_NVVM - High-level intermediate code for link-time optimization.

  Applicable options: NVVM compiler options, PTX compiler options

See Also:

• Constant Field Values

CU_GRAPHICS_REGISTER_FLAGS_NONE

public static final int CU_GRAPHICS_REGISTER_FLAGS_NONE

Flags to register a graphics resource. (CUgraphicsRegisterFlags)

Enum values:

• GRAPHICS_REGISTER_FLAGS_NONE
• GRAPHICS_REGISTER_FLAGS_READ_ONLY
• GRAPHICS_REGISTER_FLAGS_WRITE_DISCARD
• GRAPHICS_REGISTER_FLAGS_SURFACE_LDST
• GRAPHICS_REGISTER_FLAGS_TEXTURE_GATHER

See Also:

• Constant Field Values

CU_GRAPHICS_REGISTER_FLAGS_READ_ONLY

public static final int CU_GRAPHICS_REGISTER_FLAGS_READ_ONLY

Flags to register a graphics resource. (CUgraphicsRegisterFlags)

Enum values:

• GRAPHICS_REGISTER_FLAGS_NONE
• GRAPHICS_REGISTER_FLAGS_READ_ONLY
• GRAPHICS_REGISTER_FLAGS_WRITE_DISCARD
• GRAPHICS_REGISTER_FLAGS_SURFACE_LDST
• GRAPHICS_REGISTER_FLAGS_TEXTURE_GATHER

See Also:

• Constant Field Values

CU_GRAPHICS_REGISTER_FLAGS_WRITE_DISCARD

public static final int CU_GRAPHICS_REGISTER_FLAGS_WRITE_DISCARD

Flags to register a graphics resource. (CUgraphicsRegisterFlags)

Enum values:

• GRAPHICS_REGISTER_FLAGS_NONE
• GRAPHICS_REGISTER_FLAGS_READ_ONLY
• GRAPHICS_REGISTER_FLAGS_WRITE_DISCARD
• GRAPHICS_REGISTER_FLAGS_SURFACE_LDST
• GRAPHICS_REGISTER_FLAGS_TEXTURE_GATHER

See Also:

• Constant Field Values

CU_GRAPHICS_REGISTER_FLAGS_SURFACE_LDST

public static final int CU_GRAPHICS_REGISTER_FLAGS_SURFACE_LDST

Flags to register a graphics resource. (CUgraphicsRegisterFlags)

Enum values:

• GRAPHICS_REGISTER_FLAGS_NONE
• GRAPHICS_REGISTER_FLAGS_READ_ONLY
• GRAPHICS_REGISTER_FLAGS_WRITE_DISCARD
• GRAPHICS_REGISTER_FLAGS_SURFACE_LDST
• GRAPHICS_REGISTER_FLAGS_TEXTURE_GATHER

See Also:

• Constant Field Values

CU_GRAPHICS_REGISTER_FLAGS_TEXTURE_GATHER

public static final int CU_GRAPHICS_REGISTER_FLAGS_TEXTURE_GATHER

Flags to register a graphics resource. (CUgraphicsRegisterFlags)

Enum values:

• GRAPHICS_REGISTER_FLAGS_NONE
• GRAPHICS_REGISTER_FLAGS_READ_ONLY
• GRAPHICS_REGISTER_FLAGS_WRITE_DISCARD
• GRAPHICS_REGISTER_FLAGS_SURFACE_LDST
• GRAPHICS_REGISTER_FLAGS_TEXTURE_GATHER

See Also:

• Constant Field Values

CU_GRAPHICS_MAP_RESOURCE_FLAGS_NONE

public static final int CU_GRAPHICS_MAP_RESOURCE_FLAGS_NONE

Flags for mapping and unmapping interop resources. (CUgraphicsMapResourceFlags)

Enum values:

• GRAPHICS_MAP_RESOURCE_FLAGS_NONE
• GRAPHICS_MAP_RESOURCE_FLAGS_READ_ONLY
• GRAPHICS_MAP_RESOURCE_FLAGS_WRITE_DISCARD

See Also:

• Constant Field Values

CU_GRAPHICS_MAP_RESOURCE_FLAGS_READ_ONLY

public static final int CU_GRAPHICS_MAP_RESOURCE_FLAGS_READ_ONLY

Flags for mapping and unmapping interop resources. (CUgraphicsMapResourceFlags)

Enum values:

• GRAPHICS_MAP_RESOURCE_FLAGS_NONE
• GRAPHICS_MAP_RESOURCE_FLAGS_READ_ONLY
• GRAPHICS_MAP_RESOURCE_FLAGS_WRITE_DISCARD

See Also:

• Constant Field Values

CU_GRAPHICS_MAP_RESOURCE_FLAGS_WRITE_DISCARD

public static final int CU_GRAPHICS_MAP_RESOURCE_FLAGS_WRITE_DISCARD

Flags for mapping and unmapping interop resources. (CUgraphicsMapResourceFlags)

Enum values:

• GRAPHICS_MAP_RESOURCE_FLAGS_NONE
• GRAPHICS_MAP_RESOURCE_FLAGS_READ_ONLY
• GRAPHICS_MAP_RESOURCE_FLAGS_WRITE_DISCARD

See Also:

• Constant Field Values

CU_CUBEMAP_FACE_POSITIVE_X

public static final int CU_CUBEMAP_FACE_POSITIVE_X

Array indices for cube faces. (CUarray_cubemap_face)

Enum values:

• CUBEMAP_FACE_POSITIVE_X - Positive X face of cubemap
• CUBEMAP_FACE_NEGATIVE_X - Negative X face of cubemap
• CUBEMAP_FACE_POSITIVE_Y - Positive Y face of cubemap
• CUBEMAP_FACE_NEGATIVE_Y - Negative Y face of cubemap
• CUBEMAP_FACE_POSITIVE_Z - Positive Z face of cubemap
• CUBEMAP_FACE_NEGATIVE_Z - Negative Z face of cubemap

See Also:

• Constant Field Values

CU_CUBEMAP_FACE_NEGATIVE_X

public static final int CU_CUBEMAP_FACE_NEGATIVE_X

Array indices for cube faces. (CUarray_cubemap_face)

Enum values:

• CUBEMAP_FACE_POSITIVE_X - Positive X face of cubemap
• CUBEMAP_FACE_NEGATIVE_X - Negative X face of cubemap
• CUBEMAP_FACE_POSITIVE_Y - Positive Y face of cubemap
• CUBEMAP_FACE_NEGATIVE_Y - Negative Y face of cubemap
• CUBEMAP_FACE_POSITIVE_Z - Positive Z face of cubemap
• CUBEMAP_FACE_NEGATIVE_Z - Negative Z face of cubemap

See Also:

• Constant Field Values

CU_CUBEMAP_FACE_POSITIVE_Y

public static final int CU_CUBEMAP_FACE_POSITIVE_Y

Array indices for cube faces. (CUarray_cubemap_face)

Enum values:

• CUBEMAP_FACE_POSITIVE_X - Positive X face of cubemap
• CUBEMAP_FACE_NEGATIVE_X - Negative X face of cubemap
• CUBEMAP_FACE_POSITIVE_Y - Positive Y face of cubemap
• CUBEMAP_FACE_NEGATIVE_Y - Negative Y face of cubemap
• CUBEMAP_FACE_POSITIVE_Z - Positive Z face of cubemap
• CUBEMAP_FACE_NEGATIVE_Z - Negative Z face of cubemap

See Also:

• Constant Field Values

CU_CUBEMAP_FACE_NEGATIVE_Y

public static final int CU_CUBEMAP_FACE_NEGATIVE_Y

Array indices for cube faces. (CUarray_cubemap_face)

Enum values:

• CUBEMAP_FACE_POSITIVE_X - Positive X face of cubemap
• CUBEMAP_FACE_NEGATIVE_X - Negative X face of cubemap
• CUBEMAP_FACE_POSITIVE_Y - Positive Y face of cubemap
• CUBEMAP_FACE_NEGATIVE_Y - Negative Y face of cubemap
• CUBEMAP_FACE_POSITIVE_Z - Positive Z face of cubemap
• CUBEMAP_FACE_NEGATIVE_Z - Negative Z face of cubemap

See Also:

• Constant Field Values

CU_CUBEMAP_FACE_POSITIVE_Z

public static final int CU_CUBEMAP_FACE_POSITIVE_Z

Array indices for cube faces. (CUarray_cubemap_face)

Enum values:

• CUBEMAP_FACE_POSITIVE_X - Positive X face of cubemap
• CUBEMAP_FACE_NEGATIVE_X - Negative X face of cubemap
• CUBEMAP_FACE_POSITIVE_Y - Positive Y face of cubemap
• CUBEMAP_FACE_NEGATIVE_Y - Negative Y face of cubemap
• CUBEMAP_FACE_POSITIVE_Z - Positive Z face of cubemap
• CUBEMAP_FACE_NEGATIVE_Z - Negative Z face of cubemap

See Also:

• Constant Field Values

CU_CUBEMAP_FACE_NEGATIVE_Z

public static final int CU_CUBEMAP_FACE_NEGATIVE_Z

Array indices for cube faces. (CUarray_cubemap_face)

Enum values:

• CUBEMAP_FACE_POSITIVE_X - Positive X face of cubemap
• CUBEMAP_FACE_NEGATIVE_X - Negative X face of cubemap
• CUBEMAP_FACE_POSITIVE_Y - Positive Y face of cubemap
• CUBEMAP_FACE_NEGATIVE_Y - Negative Y face of cubemap
• CUBEMAP_FACE_POSITIVE_Z - Positive Z face of cubemap
• CUBEMAP_FACE_NEGATIVE_Z - Negative Z face of cubemap

See Also:

• Constant Field Values

CU_LIMIT_STACK_SIZE

public static final int CU_LIMIT_STACK_SIZE

Limits. (CUlimit)

Enum values:

• LIMIT_STACK_SIZE - GPU thread stack size
• LIMIT_PRINTF_FIFO_SIZE - GPU printf FIFO size
• LIMIT_MALLOC_HEAP_SIZE - GPU malloc heap size
• LIMIT_DEV_RUNTIME_SYNC_DEPTH - GPU device runtime launch synchronize depth
• LIMIT_DEV_RUNTIME_PENDING_LAUNCH_COUNT - GPU device runtime pending launch count
• LIMIT_MAX_L2_FETCH_GRANULARITY - A value between 0 and 128 that indicates the maximum fetch granularity of L2 (in Bytes). This is a hint
• LIMIT_PERSISTING_L2_CACHE_SIZE - A size in bytes for L2 persisting lines cache size

See Also:

• Constant Field Values

CU_LIMIT_PRINTF_FIFO_SIZE

public static final int CU_LIMIT_PRINTF_FIFO_SIZE

Limits. (CUlimit)

Enum values:

• LIMIT_STACK_SIZE - GPU thread stack size
• LIMIT_PRINTF_FIFO_SIZE - GPU printf FIFO size
• LIMIT_MALLOC_HEAP_SIZE - GPU malloc heap size
• LIMIT_DEV_RUNTIME_SYNC_DEPTH - GPU device runtime launch synchronize depth
• LIMIT_DEV_RUNTIME_PENDING_LAUNCH_COUNT - GPU device runtime pending launch count
• LIMIT_MAX_L2_FETCH_GRANULARITY - A value between 0 and 128 that indicates the maximum fetch granularity of L2 (in Bytes). This is a hint
• LIMIT_PERSISTING_L2_CACHE_SIZE - A size in bytes for L2 persisting lines cache size

See Also:

• Constant Field Values

CU_LIMIT_MALLOC_HEAP_SIZE

public static final int CU_LIMIT_MALLOC_HEAP_SIZE

Limits. (CUlimit)

Enum values:

• LIMIT_STACK_SIZE - GPU thread stack size
• LIMIT_PRINTF_FIFO_SIZE - GPU printf FIFO size
• LIMIT_MALLOC_HEAP_SIZE - GPU malloc heap size
• LIMIT_DEV_RUNTIME_SYNC_DEPTH - GPU device runtime launch synchronize depth
• LIMIT_DEV_RUNTIME_PENDING_LAUNCH_COUNT - GPU device runtime pending launch count
• LIMIT_MAX_L2_FETCH_GRANULARITY - A value between 0 and 128 that indicates the maximum fetch granularity of L2 (in Bytes). This is a hint
• LIMIT_PERSISTING_L2_CACHE_SIZE - A size in bytes for L2 persisting lines cache size

See Also:

• Constant Field Values

CU_LIMIT_DEV_RUNTIME_SYNC_DEPTH

public static final int CU_LIMIT_DEV_RUNTIME_SYNC_DEPTH

Limits. (CUlimit)

Enum values:

• LIMIT_STACK_SIZE - GPU thread stack size
• LIMIT_PRINTF_FIFO_SIZE - GPU printf FIFO size
• LIMIT_MALLOC_HEAP_SIZE - GPU malloc heap size
• LIMIT_DEV_RUNTIME_SYNC_DEPTH - GPU device runtime launch synchronize depth
• LIMIT_DEV_RUNTIME_PENDING_LAUNCH_COUNT - GPU device runtime pending launch count
• LIMIT_MAX_L2_FETCH_GRANULARITY - A value between 0 and 128 that indicates the maximum fetch granularity of L2 (in Bytes). This is a hint
• LIMIT_PERSISTING_L2_CACHE_SIZE - A size in bytes for L2 persisting lines cache size

See Also:

• Constant Field Values

CU_LIMIT_DEV_RUNTIME_PENDING_LAUNCH_COUNT

public static final int CU_LIMIT_DEV_RUNTIME_PENDING_LAUNCH_COUNT

Limits. (CUlimit)

Enum values:

• LIMIT_STACK_SIZE - GPU thread stack size
• LIMIT_PRINTF_FIFO_SIZE - GPU printf FIFO size
• LIMIT_MALLOC_HEAP_SIZE - GPU malloc heap size
• LIMIT_DEV_RUNTIME_SYNC_DEPTH - GPU device runtime launch synchronize depth
• LIMIT_DEV_RUNTIME_PENDING_LAUNCH_COUNT - GPU device runtime pending launch count
• LIMIT_MAX_L2_FETCH_GRANULARITY - A value between 0 and 128 that indicates the maximum fetch granularity of L2 (in Bytes). This is a hint
• LIMIT_PERSISTING_L2_CACHE_SIZE - A size in bytes for L2 persisting lines cache size

See Also:

• Constant Field Values

CU_LIMIT_MAX_L2_FETCH_GRANULARITY

public static final int CU_LIMIT_MAX_L2_FETCH_GRANULARITY

Limits. (CUlimit)

Enum values:

• LIMIT_STACK_SIZE - GPU thread stack size
• LIMIT_PRINTF_FIFO_SIZE - GPU printf FIFO size
• LIMIT_MALLOC_HEAP_SIZE - GPU malloc heap size
• LIMIT_DEV_RUNTIME_SYNC_DEPTH - GPU device runtime launch synchronize depth
• LIMIT_DEV_RUNTIME_PENDING_LAUNCH_COUNT - GPU device runtime pending launch count
• LIMIT_MAX_L2_FETCH_GRANULARITY - A value between 0 and 128 that indicates the maximum fetch granularity of L2 (in Bytes). This is a hint
• LIMIT_PERSISTING_L2_CACHE_SIZE - A size in bytes for L2 persisting lines cache size

See Also:

• Constant Field Values

CU_LIMIT_PERSISTING_L2_CACHE_SIZE

public static final int CU_LIMIT_PERSISTING_L2_CACHE_SIZE

Limits. (CUlimit)

Enum values:

• LIMIT_STACK_SIZE - GPU thread stack size
• LIMIT_PRINTF_FIFO_SIZE - GPU printf FIFO size
• LIMIT_MALLOC_HEAP_SIZE - GPU malloc heap size
• LIMIT_DEV_RUNTIME_SYNC_DEPTH - GPU device runtime launch synchronize depth
• LIMIT_DEV_RUNTIME_PENDING_LAUNCH_COUNT - GPU device runtime pending launch count
• LIMIT_MAX_L2_FETCH_GRANULARITY - A value between 0 and 128 that indicates the maximum fetch granularity of L2 (in Bytes). This is a hint
• LIMIT_PERSISTING_L2_CACHE_SIZE - A size in bytes for L2 persisting lines cache size

See Also:

• Constant Field Values

CU_RESOURCE_TYPE_ARRAY

public static final int CU_RESOURCE_TYPE_ARRAY

Resource types. (CUresourcetype)

Enum values:

• RESOURCE_TYPE_ARRAY - Array resoure
• RESOURCE_TYPE_MIPMAPPED_ARRAY - Mipmapped array resource
• RESOURCE_TYPE_LINEAR - Linear resource
• RESOURCE_TYPE_PITCH2D - Pitch 2D resource

See Also:

• Constant Field Values

CU_RESOURCE_TYPE_MIPMAPPED_ARRAY

public static final int CU_RESOURCE_TYPE_MIPMAPPED_ARRAY

Resource types. (CUresourcetype)

Enum values:

• RESOURCE_TYPE_ARRAY - Array resoure
• RESOURCE_TYPE_MIPMAPPED_ARRAY - Mipmapped array resource
• RESOURCE_TYPE_LINEAR - Linear resource
• RESOURCE_TYPE_PITCH2D - Pitch 2D resource

See Also:

• Constant Field Values

CU_RESOURCE_TYPE_LINEAR

public static final int CU_RESOURCE_TYPE_LINEAR

Resource types. (CUresourcetype)

Enum values:

• RESOURCE_TYPE_ARRAY - Array resoure
• RESOURCE_TYPE_MIPMAPPED_ARRAY - Mipmapped array resource
• RESOURCE_TYPE_LINEAR - Linear resource
• RESOURCE_TYPE_PITCH2D - Pitch 2D resource

See Also:

• Constant Field Values

CU_RESOURCE_TYPE_PITCH2D

public static final int CU_RESOURCE_TYPE_PITCH2D

Resource types. (CUresourcetype)

Enum values:

• RESOURCE_TYPE_ARRAY - Array resoure
• RESOURCE_TYPE_MIPMAPPED_ARRAY - Mipmapped array resource
• RESOURCE_TYPE_LINEAR - Linear resource
• RESOURCE_TYPE_PITCH2D - Pitch 2D resource

See Also:

• Constant Field Values

CU_ACCESS_PROPERTY_NORMAL

public static final int CU_ACCESS_PROPERTY_NORMAL

Specifies performance hint with CUaccessPolicyWindow for hitProp and missProp members. (CUaccessProperty)

Enum values:

• ACCESS_PROPERTY_NORMAL - Normal cache persistence.
• ACCESS_PROPERTY_STREAMING - Streaming access is less likely to persit from cache.
• ACCESS_PROPERTY_PERSISTING - Persisting access is more likely to persist in cache.

See Also:

• Constant Field Values

CU_ACCESS_PROPERTY_STREAMING

public static final int CU_ACCESS_PROPERTY_STREAMING

Specifies performance hint with CUaccessPolicyWindow for hitProp and missProp members. (CUaccessProperty)

Enum values:

• ACCESS_PROPERTY_NORMAL - Normal cache persistence.
• ACCESS_PROPERTY_STREAMING - Streaming access is less likely to persit from cache.
• ACCESS_PROPERTY_PERSISTING - Persisting access is more likely to persist in cache.

See Also:

• Constant Field Values

CU_ACCESS_PROPERTY_PERSISTING

public static final int CU_ACCESS_PROPERTY_PERSISTING

Specifies performance hint with CUaccessPolicyWindow for hitProp and missProp members. (CUaccessProperty)

Enum values:

• ACCESS_PROPERTY_NORMAL - Normal cache persistence.
• ACCESS_PROPERTY_STREAMING - Streaming access is less likely to persit from cache.
• ACCESS_PROPERTY_PERSISTING - Persisting access is more likely to persist in cache.

See Also:

• Constant Field Values

CU_GRAPH_NODE_TYPE_KERNEL

public static final int CU_GRAPH_NODE_TYPE_KERNEL

Graph node types. (CUgraphNodeType)

Enum values:

• GRAPH_NODE_TYPE_KERNEL - GPU kernel node
• GRAPH_NODE_TYPE_MEMCPY - Memcpy node
• GRAPH_NODE_TYPE_MEMSET - Memset node
• GRAPH_NODE_TYPE_HOST - Host (executable) node
• GRAPH_NODE_TYPE_GRAPH - Node which executes an embedded graph
• GRAPH_NODE_TYPE_EMPTY - Empty (no-op) node
• GRAPH_NODE_TYPE_WAIT_EVENT - External event wait node
• GRAPH_NODE_TYPE_EVENT_RECORD - External event record node
• GRAPH_NODE_TYPE_EXT_SEMAS_SIGNAL - External semaphore signal node
• GRAPH_NODE_TYPE_EXT_SEMAS_WAIT - External semaphore wait node
• GRAPH_NODE_TYPE_MEM_ALLOC - Memory Allocation Node
• GRAPH_NODE_TYPE_MEM_FREE - Memory Free Node

See Also:

• Constant Field Values

CU_GRAPH_NODE_TYPE_MEMCPY

public static final int CU_GRAPH_NODE_TYPE_MEMCPY

Graph node types. (CUgraphNodeType)

Enum values:

• GRAPH_NODE_TYPE_KERNEL - GPU kernel node
• GRAPH_NODE_TYPE_MEMCPY - Memcpy node
• GRAPH_NODE_TYPE_MEMSET - Memset node
• GRAPH_NODE_TYPE_HOST - Host (executable) node
• GRAPH_NODE_TYPE_GRAPH - Node which executes an embedded graph
• GRAPH_NODE_TYPE_EMPTY - Empty (no-op) node
• GRAPH_NODE_TYPE_WAIT_EVENT - External event wait node
• GRAPH_NODE_TYPE_EVENT_RECORD - External event record node
• GRAPH_NODE_TYPE_EXT_SEMAS_SIGNAL - External semaphore signal node
• GRAPH_NODE_TYPE_EXT_SEMAS_WAIT - External semaphore wait node
• GRAPH_NODE_TYPE_MEM_ALLOC - Memory Allocation Node
• GRAPH_NODE_TYPE_MEM_FREE - Memory Free Node

See Also:

• Constant Field Values

CU_GRAPH_NODE_TYPE_MEMSET

public static final int CU_GRAPH_NODE_TYPE_MEMSET

Graph node types. (CUgraphNodeType)

Enum values:

• GRAPH_NODE_TYPE_KERNEL - GPU kernel node
• GRAPH_NODE_TYPE_MEMCPY - Memcpy node
• GRAPH_NODE_TYPE_MEMSET - Memset node
• GRAPH_NODE_TYPE_HOST - Host (executable) node
• GRAPH_NODE_TYPE_GRAPH - Node which executes an embedded graph
• GRAPH_NODE_TYPE_EMPTY - Empty (no-op) node
• GRAPH_NODE_TYPE_WAIT_EVENT - External event wait node
• GRAPH_NODE_TYPE_EVENT_RECORD - External event record node
• GRAPH_NODE_TYPE_EXT_SEMAS_SIGNAL - External semaphore signal node
• GRAPH_NODE_TYPE_EXT_SEMAS_WAIT - External semaphore wait node
• GRAPH_NODE_TYPE_MEM_ALLOC - Memory Allocation Node
• GRAPH_NODE_TYPE_MEM_FREE - Memory Free Node

See Also:

• Constant Field Values

CU_GRAPH_NODE_TYPE_HOST

public static final int CU_GRAPH_NODE_TYPE_HOST

Graph node types. (CUgraphNodeType)

Enum values:

• GRAPH_NODE_TYPE_KERNEL - GPU kernel node
• GRAPH_NODE_TYPE_MEMCPY - Memcpy node
• GRAPH_NODE_TYPE_MEMSET - Memset node
• GRAPH_NODE_TYPE_HOST - Host (executable) node
• GRAPH_NODE_TYPE_GRAPH - Node which executes an embedded graph
• GRAPH_NODE_TYPE_EMPTY - Empty (no-op) node
• GRAPH_NODE_TYPE_WAIT_EVENT - External event wait node
• GRAPH_NODE_TYPE_EVENT_RECORD - External event record node
• GRAPH_NODE_TYPE_EXT_SEMAS_SIGNAL - External semaphore signal node
• GRAPH_NODE_TYPE_EXT_SEMAS_WAIT - External semaphore wait node
• GRAPH_NODE_TYPE_MEM_ALLOC - Memory Allocation Node
• GRAPH_NODE_TYPE_MEM_FREE - Memory Free Node

See Also:

• Constant Field Values

CU_GRAPH_NODE_TYPE_GRAPH

public static final int CU_GRAPH_NODE_TYPE_GRAPH

Graph node types. (CUgraphNodeType)

Enum values:

• GRAPH_NODE_TYPE_KERNEL - GPU kernel node
• GRAPH_NODE_TYPE_MEMCPY - Memcpy node
• GRAPH_NODE_TYPE_MEMSET - Memset node
• GRAPH_NODE_TYPE_HOST - Host (executable) node
• GRAPH_NODE_TYPE_GRAPH - Node which executes an embedded graph
• GRAPH_NODE_TYPE_EMPTY - Empty (no-op) node
• GRAPH_NODE_TYPE_WAIT_EVENT - External event wait node
• GRAPH_NODE_TYPE_EVENT_RECORD - External event record node
• GRAPH_NODE_TYPE_EXT_SEMAS_SIGNAL - External semaphore signal node
• GRAPH_NODE_TYPE_EXT_SEMAS_WAIT - External semaphore wait node
• GRAPH_NODE_TYPE_MEM_ALLOC - Memory Allocation Node
• GRAPH_NODE_TYPE_MEM_FREE - Memory Free Node

See Also:

• Constant Field Values

CU_GRAPH_NODE_TYPE_EMPTY

public static final int CU_GRAPH_NODE_TYPE_EMPTY

Graph node types. (CUgraphNodeType)

Enum values:

• GRAPH_NODE_TYPE_KERNEL - GPU kernel node
• GRAPH_NODE_TYPE_MEMCPY - Memcpy node
• GRAPH_NODE_TYPE_MEMSET - Memset node
• GRAPH_NODE_TYPE_HOST - Host (executable) node
• GRAPH_NODE_TYPE_GRAPH - Node which executes an embedded graph
• GRAPH_NODE_TYPE_EMPTY - Empty (no-op) node
• GRAPH_NODE_TYPE_WAIT_EVENT - External event wait node
• GRAPH_NODE_TYPE_EVENT_RECORD - External event record node
• GRAPH_NODE_TYPE_EXT_SEMAS_SIGNAL - External semaphore signal node
• GRAPH_NODE_TYPE_EXT_SEMAS_WAIT - External semaphore wait node
• GRAPH_NODE_TYPE_MEM_ALLOC - Memory Allocation Node
• GRAPH_NODE_TYPE_MEM_FREE - Memory Free Node

See Also:

• Constant Field Values

CU_GRAPH_NODE_TYPE_WAIT_EVENT

public static final int CU_GRAPH_NODE_TYPE_WAIT_EVENT

Graph node types. (CUgraphNodeType)

Enum values:

• GRAPH_NODE_TYPE_KERNEL - GPU kernel node
• GRAPH_NODE_TYPE_MEMCPY - Memcpy node
• GRAPH_NODE_TYPE_MEMSET - Memset node
• GRAPH_NODE_TYPE_HOST - Host (executable) node
• GRAPH_NODE_TYPE_GRAPH - Node which executes an embedded graph
• GRAPH_NODE_TYPE_EMPTY - Empty (no-op) node
• GRAPH_NODE_TYPE_WAIT_EVENT - External event wait node
• GRAPH_NODE_TYPE_EVENT_RECORD - External event record node
• GRAPH_NODE_TYPE_EXT_SEMAS_SIGNAL - External semaphore signal node
• GRAPH_NODE_TYPE_EXT_SEMAS_WAIT - External semaphore wait node
• GRAPH_NODE_TYPE_MEM_ALLOC - Memory Allocation Node
• GRAPH_NODE_TYPE_MEM_FREE - Memory Free Node

See Also:

• Constant Field Values

CU_GRAPH_NODE_TYPE_EVENT_RECORD

public static final int CU_GRAPH_NODE_TYPE_EVENT_RECORD

Graph node types. (CUgraphNodeType)

Enum values:

• GRAPH_NODE_TYPE_KERNEL - GPU kernel node
• GRAPH_NODE_TYPE_MEMCPY - Memcpy node
• GRAPH_NODE_TYPE_MEMSET - Memset node
• GRAPH_NODE_TYPE_HOST - Host (executable) node
• GRAPH_NODE_TYPE_GRAPH - Node which executes an embedded graph
• GRAPH_NODE_TYPE_EMPTY - Empty (no-op) node
• GRAPH_NODE_TYPE_WAIT_EVENT - External event wait node
• GRAPH_NODE_TYPE_EVENT_RECORD - External event record node
• GRAPH_NODE_TYPE_EXT_SEMAS_SIGNAL - External semaphore signal node
• GRAPH_NODE_TYPE_EXT_SEMAS_WAIT - External semaphore wait node
• GRAPH_NODE_TYPE_MEM_ALLOC - Memory Allocation Node
• GRAPH_NODE_TYPE_MEM_FREE - Memory Free Node

See Also:

• Constant Field Values

CU_GRAPH_NODE_TYPE_EXT_SEMAS_SIGNAL

public static final int CU_GRAPH_NODE_TYPE_EXT_SEMAS_SIGNAL

Graph node types. (CUgraphNodeType)

Enum values:

• GRAPH_NODE_TYPE_KERNEL - GPU kernel node
• GRAPH_NODE_TYPE_MEMCPY - Memcpy node
• GRAPH_NODE_TYPE_MEMSET - Memset node
• GRAPH_NODE_TYPE_HOST - Host (executable) node
• GRAPH_NODE_TYPE_GRAPH - Node which executes an embedded graph
• GRAPH_NODE_TYPE_EMPTY - Empty (no-op) node
• GRAPH_NODE_TYPE_WAIT_EVENT - External event wait node
• GRAPH_NODE_TYPE_EVENT_RECORD - External event record node
• GRAPH_NODE_TYPE_EXT_SEMAS_SIGNAL - External semaphore signal node
• GRAPH_NODE_TYPE_EXT_SEMAS_WAIT - External semaphore wait node
• GRAPH_NODE_TYPE_MEM_ALLOC - Memory Allocation Node
• GRAPH_NODE_TYPE_MEM_FREE - Memory Free Node

See Also:

• Constant Field Values

CU_GRAPH_NODE_TYPE_EXT_SEMAS_WAIT

public static final int CU_GRAPH_NODE_TYPE_EXT_SEMAS_WAIT

Graph node types. (CUgraphNodeType)

Enum values:

• GRAPH_NODE_TYPE_KERNEL - GPU kernel node
• GRAPH_NODE_TYPE_MEMCPY - Memcpy node
• GRAPH_NODE_TYPE_MEMSET - Memset node
• GRAPH_NODE_TYPE_HOST - Host (executable) node
• GRAPH_NODE_TYPE_GRAPH - Node which executes an embedded graph
• GRAPH_NODE_TYPE_EMPTY - Empty (no-op) node
• GRAPH_NODE_TYPE_WAIT_EVENT - External event wait node
• GRAPH_NODE_TYPE_EVENT_RECORD - External event record node
• GRAPH_NODE_TYPE_EXT_SEMAS_SIGNAL - External semaphore signal node
• GRAPH_NODE_TYPE_EXT_SEMAS_WAIT - External semaphore wait node
• GRAPH_NODE_TYPE_MEM_ALLOC - Memory Allocation Node
• GRAPH_NODE_TYPE_MEM_FREE - Memory Free Node

See Also:

• Constant Field Values

CU_GRAPH_NODE_TYPE_MEM_ALLOC

public static final int CU_GRAPH_NODE_TYPE_MEM_ALLOC

Graph node types. (CUgraphNodeType)

Enum values:

• GRAPH_NODE_TYPE_KERNEL - GPU kernel node
• GRAPH_NODE_TYPE_MEMCPY - Memcpy node
• GRAPH_NODE_TYPE_MEMSET - Memset node
• GRAPH_NODE_TYPE_HOST - Host (executable) node
• GRAPH_NODE_TYPE_GRAPH - Node which executes an embedded graph
• GRAPH_NODE_TYPE_EMPTY - Empty (no-op) node
• GRAPH_NODE_TYPE_WAIT_EVENT - External event wait node
• GRAPH_NODE_TYPE_EVENT_RECORD - External event record node
• GRAPH_NODE_TYPE_EXT_SEMAS_SIGNAL - External semaphore signal node
• GRAPH_NODE_TYPE_EXT_SEMAS_WAIT - External semaphore wait node
• GRAPH_NODE_TYPE_MEM_ALLOC - Memory Allocation Node
• GRAPH_NODE_TYPE_MEM_FREE - Memory Free Node

See Also:

• Constant Field Values

CU_GRAPH_NODE_TYPE_MEM_FREE

public static final int CU_GRAPH_NODE_TYPE_MEM_FREE

Graph node types. (CUgraphNodeType)

Enum values:

• GRAPH_NODE_TYPE_KERNEL - GPU kernel node
• GRAPH_NODE_TYPE_MEMCPY - Memcpy node
• GRAPH_NODE_TYPE_MEMSET - Memset node
• GRAPH_NODE_TYPE_HOST - Host (executable) node
• GRAPH_NODE_TYPE_GRAPH - Node which executes an embedded graph
• GRAPH_NODE_TYPE_EMPTY - Empty (no-op) node
• GRAPH_NODE_TYPE_WAIT_EVENT - External event wait node
• GRAPH_NODE_TYPE_EVENT_RECORD - External event record node
• GRAPH_NODE_TYPE_EXT_SEMAS_SIGNAL - External semaphore signal node
• GRAPH_NODE_TYPE_EXT_SEMAS_WAIT - External semaphore wait node
• GRAPH_NODE_TYPE_MEM_ALLOC - Memory Allocation Node
• GRAPH_NODE_TYPE_MEM_FREE - Memory Free Node

See Also:

• Constant Field Values

CU_SYNC_POLICY_AUTO

public static final int CU_SYNC_POLICY_AUTO

CUsynchronizationPolicy

Enum values:

• SYNC_POLICY_AUTO
• SYNC_POLICY_SPIN
• SYNC_POLICY_YIELD
• SYNC_POLICY_BLOCKING_SYNC

See Also:

• Constant Field Values

CU_SYNC_POLICY_SPIN

public static final int CU_SYNC_POLICY_SPIN

CUsynchronizationPolicy

Enum values:

• SYNC_POLICY_AUTO
• SYNC_POLICY_SPIN
• SYNC_POLICY_YIELD
• SYNC_POLICY_BLOCKING_SYNC

See Also:

• Constant Field Values

CU_SYNC_POLICY_YIELD

public static final int CU_SYNC_POLICY_YIELD

CUsynchronizationPolicy

Enum values:

• SYNC_POLICY_AUTO
• SYNC_POLICY_SPIN
• SYNC_POLICY_YIELD
• SYNC_POLICY_BLOCKING_SYNC

See Also:

• Constant Field Values

CU_SYNC_POLICY_BLOCKING_SYNC

public static final int CU_SYNC_POLICY_BLOCKING_SYNC

CUsynchronizationPolicy

Enum values:

• SYNC_POLICY_AUTO
• SYNC_POLICY_SPIN
• SYNC_POLICY_YIELD
• SYNC_POLICY_BLOCKING_SYNC

See Also:

• Constant Field Values

CU_KERNEL_NODE_ATTRIBUTE_ACCESS_POLICY_WINDOW

public static final int CU_KERNEL_NODE_ATTRIBUTE_ACCESS_POLICY_WINDOW

Graph kernel node Attributes (CUkernelNodeAttrID)

Enum values:

• KERNEL_NODE_ATTRIBUTE_ACCESS_POLICY_WINDOW - Identifier for CUkernelNodeAttrValue{@code accessPolicyWindow}.
• KERNEL_NODE_ATTRIBUTE_COOPERATIVE - Allows a kernel node to be cooperative (see LaunchCooperativeKernel).

See Also:

• Constant Field Values

CU_KERNEL_NODE_ATTRIBUTE_COOPERATIVE

public static final int CU_KERNEL_NODE_ATTRIBUTE_COOPERATIVE

Graph kernel node Attributes (CUkernelNodeAttrID)

Enum values:

• KERNEL_NODE_ATTRIBUTE_ACCESS_POLICY_WINDOW - Identifier for CUkernelNodeAttrValue{@code accessPolicyWindow}.
• KERNEL_NODE_ATTRIBUTE_COOPERATIVE - Allows a kernel node to be cooperative (see LaunchCooperativeKernel).

See Also:

• Constant Field Values

CU_STREAM_CAPTURE_STATUS_NONE

public static final int CU_STREAM_CAPTURE_STATUS_NONE

Possible stream capture statuses returned by StreamIsCapturing. (CUstreamCaptureStatus)

Enum values:

• STREAM_CAPTURE_STATUS_NONE - Stream is not capturing
• STREAM_CAPTURE_STATUS_ACTIVE - Stream is actively capturing
• STREAM_CAPTURE_STATUS_INVALIDATED - Stream is part of a capture sequence that has been invalidated, but not terminated

See Also:

• Constant Field Values

CU_STREAM_CAPTURE_STATUS_ACTIVE

public static final int CU_STREAM_CAPTURE_STATUS_ACTIVE

Possible stream capture statuses returned by StreamIsCapturing. (CUstreamCaptureStatus)

Enum values:

• STREAM_CAPTURE_STATUS_NONE - Stream is not capturing
• STREAM_CAPTURE_STATUS_ACTIVE - Stream is actively capturing
• STREAM_CAPTURE_STATUS_INVALIDATED - Stream is part of a capture sequence that has been invalidated, but not terminated

See Also:

• Constant Field Values

CU_STREAM_CAPTURE_STATUS_INVALIDATED

public static final int CU_STREAM_CAPTURE_STATUS_INVALIDATED

Possible stream capture statuses returned by StreamIsCapturing. (CUstreamCaptureStatus)

Enum values:

• STREAM_CAPTURE_STATUS_NONE - Stream is not capturing
• STREAM_CAPTURE_STATUS_ACTIVE - Stream is actively capturing
• STREAM_CAPTURE_STATUS_INVALIDATED - Stream is part of a capture sequence that has been invalidated, but not terminated

See Also:

• Constant Field Values

CU_STREAM_CAPTURE_MODE_GLOBAL

public static final int CU_STREAM_CAPTURE_MODE_GLOBAL

Possible modes for stream capture thread interactions. (CUstreamCaptureMode)

For more details see StreamBeginCapture and ThreadExchangeStreamCaptureMode

Enum values:

• STREAM_CAPTURE_MODE_GLOBAL
• STREAM_CAPTURE_MODE_THREAD_LOCAL
• STREAM_CAPTURE_MODE_RELAXED

See Also:

• Constant Field Values

CU_STREAM_CAPTURE_MODE_THREAD_LOCAL

public static final int CU_STREAM_CAPTURE_MODE_THREAD_LOCAL

Possible modes for stream capture thread interactions. (CUstreamCaptureMode)

For more details see StreamBeginCapture and ThreadExchangeStreamCaptureMode

Enum values:

• STREAM_CAPTURE_MODE_GLOBAL
• STREAM_CAPTURE_MODE_THREAD_LOCAL
• STREAM_CAPTURE_MODE_RELAXED

See Also:

• Constant Field Values

CU_STREAM_CAPTURE_MODE_RELAXED

public static final int CU_STREAM_CAPTURE_MODE_RELAXED

Possible modes for stream capture thread interactions. (CUstreamCaptureMode)

For more details see StreamBeginCapture and ThreadExchangeStreamCaptureMode

Enum values:

• STREAM_CAPTURE_MODE_GLOBAL
• STREAM_CAPTURE_MODE_THREAD_LOCAL
• STREAM_CAPTURE_MODE_RELAXED

See Also:

• Constant Field Values

CU_STREAM_ATTRIBUTE_ACCESS_POLICY_WINDOW

public static final int CU_STREAM_ATTRIBUTE_ACCESS_POLICY_WINDOW

Stream Attributes (CUstreamAttrID)

Enum values:

• STREAM_ATTRIBUTE_ACCESS_POLICY_WINDOW - Identifier for CUstreamAttrValue{@code accessPolicyWindow}.
• STREAM_ATTRIBUTE_SYNCHRONIZATION_POLICY - CUsynchronizationPolicy for work queued up in this stream

See Also:

• Constant Field Values

CU_STREAM_ATTRIBUTE_SYNCHRONIZATION_POLICY

public static final int CU_STREAM_ATTRIBUTE_SYNCHRONIZATION_POLICY

Stream Attributes (CUstreamAttrID)

Enum values:

• STREAM_ATTRIBUTE_ACCESS_POLICY_WINDOW - Identifier for CUstreamAttrValue{@code accessPolicyWindow}.
• STREAM_ATTRIBUTE_SYNCHRONIZATION_POLICY - CUsynchronizationPolicy for work queued up in this stream

See Also:

• Constant Field Values

CU_GET_PROC_ADDRESS_DEFAULT

public static final int CU_GET_PROC_ADDRESS_DEFAULT

Flags to specify search options. For more details see GetProcAddress. (CUdriverProcAddress_flags)

Enum values:

• GET_PROC_ADDRESS_DEFAULT - Default search mode for driver symbols.
• GET_PROC_ADDRESS_LEGACY_STREAM - Search for legacy versions of driver symbols.
• GET_PROC_ADDRESS_PER_THREAD_DEFAULT_STREAM - Search for per-thread versions of driver symbols.

See Also:

• Constant Field Values

CU_GET_PROC_ADDRESS_LEGACY_STREAM

public static final int CU_GET_PROC_ADDRESS_LEGACY_STREAM

Flags to specify search options. For more details see GetProcAddress. (CUdriverProcAddress_flags)

Enum values:

• GET_PROC_ADDRESS_DEFAULT - Default search mode for driver symbols.
• GET_PROC_ADDRESS_LEGACY_STREAM - Search for legacy versions of driver symbols.
• GET_PROC_ADDRESS_PER_THREAD_DEFAULT_STREAM - Search for per-thread versions of driver symbols.

See Also:

• Constant Field Values

CU_GET_PROC_ADDRESS_PER_THREAD_DEFAULT_STREAM

public static final int CU_GET_PROC_ADDRESS_PER_THREAD_DEFAULT_STREAM

Flags to specify search options. For more details see GetProcAddress. (CUdriverProcAddress_flags)

Enum values:

• GET_PROC_ADDRESS_DEFAULT - Default search mode for driver symbols.
• GET_PROC_ADDRESS_LEGACY_STREAM - Search for legacy versions of driver symbols.
• GET_PROC_ADDRESS_PER_THREAD_DEFAULT_STREAM - Search for per-thread versions of driver symbols.

See Also:

• Constant Field Values

CU_EXEC_AFFINITY_TYPE_SM_COUNT

public static final int CU_EXEC_AFFINITY_TYPE_SM_COUNT

Execution Affinity Types

(CUexecAffinityType)

Enum values:

• EXEC_AFFINITY_TYPE_SM_COUNT - Create a context with limited SMs.
• EXEC_AFFINITY_TYPE_MAX

See Also:

• Constant Field Values

CU_EXEC_AFFINITY_TYPE_MAX

public static final int CU_EXEC_AFFINITY_TYPE_MAX

Execution Affinity Types

(CUexecAffinityType)

Enum values:

• EXEC_AFFINITY_TYPE_SM_COUNT - Create a context with limited SMs.
• EXEC_AFFINITY_TYPE_MAX

See Also:

• Constant Field Values

CUDA_SUCCESS

public static final int CUDA_SUCCESS

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_INVALID_VALUE

public static final int CUDA_ERROR_INVALID_VALUE

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_OUT_OF_MEMORY

public static final int CUDA_ERROR_OUT_OF_MEMORY

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_NOT_INITIALIZED

public static final int CUDA_ERROR_NOT_INITIALIZED

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_DEINITIALIZED

public static final int CUDA_ERROR_DEINITIALIZED

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_PROFILER_DISABLED

public static final int CUDA_ERROR_PROFILER_DISABLED

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_PROFILER_NOT_INITIALIZED

public static final int CUDA_ERROR_PROFILER_NOT_INITIALIZED

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_PROFILER_ALREADY_STARTED

public static final int CUDA_ERROR_PROFILER_ALREADY_STARTED

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_PROFILER_ALREADY_STOPPED

public static final int CUDA_ERROR_PROFILER_ALREADY_STOPPED

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_STUB_LIBRARY

public static final int CUDA_ERROR_STUB_LIBRARY

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_NO_DEVICE

public static final int CUDA_ERROR_NO_DEVICE

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_INVALID_DEVICE

public static final int CUDA_ERROR_INVALID_DEVICE

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_DEVICE_NOT_LICENSED

public static final int CUDA_ERROR_DEVICE_NOT_LICENSED

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_INVALID_IMAGE

public static final int CUDA_ERROR_INVALID_IMAGE

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_INVALID_CONTEXT

public static final int CUDA_ERROR_INVALID_CONTEXT

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_CONTEXT_ALREADY_CURRENT

public static final int CUDA_ERROR_CONTEXT_ALREADY_CURRENT

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_MAP_FAILED

public static final int CUDA_ERROR_MAP_FAILED

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_UNMAP_FAILED

public static final int CUDA_ERROR_UNMAP_FAILED

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_ARRAY_IS_MAPPED

public static final int CUDA_ERROR_ARRAY_IS_MAPPED

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_ALREADY_MAPPED

public static final int CUDA_ERROR_ALREADY_MAPPED

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_NO_BINARY_FOR_GPU

public static final int CUDA_ERROR_NO_BINARY_FOR_GPU

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_ALREADY_ACQUIRED

public static final int CUDA_ERROR_ALREADY_ACQUIRED

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_NOT_MAPPED

public static final int CUDA_ERROR_NOT_MAPPED

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_NOT_MAPPED_AS_ARRAY

public static final int CUDA_ERROR_NOT_MAPPED_AS_ARRAY

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_NOT_MAPPED_AS_POINTER

public static final int CUDA_ERROR_NOT_MAPPED_AS_POINTER

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_ECC_UNCORRECTABLE

public static final int CUDA_ERROR_ECC_UNCORRECTABLE

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_UNSUPPORTED_LIMIT

public static final int CUDA_ERROR_UNSUPPORTED_LIMIT

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_CONTEXT_ALREADY_IN_USE

public static final int CUDA_ERROR_CONTEXT_ALREADY_IN_USE

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_PEER_ACCESS_UNSUPPORTED

public static final int CUDA_ERROR_PEER_ACCESS_UNSUPPORTED

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_INVALID_PTX

public static final int CUDA_ERROR_INVALID_PTX

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_INVALID_GRAPHICS_CONTEXT

public static final int CUDA_ERROR_INVALID_GRAPHICS_CONTEXT

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_NVLINK_UNCORRECTABLE

public static final int CUDA_ERROR_NVLINK_UNCORRECTABLE

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_JIT_COMPILER_NOT_FOUND

public static final int CUDA_ERROR_JIT_COMPILER_NOT_FOUND

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_UNSUPPORTED_PTX_VERSION

public static final int CUDA_ERROR_UNSUPPORTED_PTX_VERSION

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_JIT_COMPILATION_DISABLED

public static final int CUDA_ERROR_JIT_COMPILATION_DISABLED

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY

public static final int CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_INVALID_SOURCE

public static final int CUDA_ERROR_INVALID_SOURCE

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_FILE_NOT_FOUND

public static final int CUDA_ERROR_FILE_NOT_FOUND

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND

public static final int CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_SHARED_OBJECT_INIT_FAILED

public static final int CUDA_ERROR_SHARED_OBJECT_INIT_FAILED

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_OPERATING_SYSTEM

public static final int CUDA_ERROR_OPERATING_SYSTEM

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_INVALID_HANDLE

public static final int CUDA_ERROR_INVALID_HANDLE

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_ILLEGAL_STATE

public static final int CUDA_ERROR_ILLEGAL_STATE

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_NOT_FOUND

public static final int CUDA_ERROR_NOT_FOUND

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_NOT_READY

public static final int CUDA_ERROR_NOT_READY

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_ILLEGAL_ADDRESS

public static final int CUDA_ERROR_ILLEGAL_ADDRESS

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES

public static final int CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_LAUNCH_TIMEOUT

public static final int CUDA_ERROR_LAUNCH_TIMEOUT

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING

public static final int CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED

public static final int CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_PEER_ACCESS_NOT_ENABLED

public static final int CUDA_ERROR_PEER_ACCESS_NOT_ENABLED

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE

public static final int CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_CONTEXT_IS_DESTROYED

public static final int CUDA_ERROR_CONTEXT_IS_DESTROYED

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_ASSERT

public static final int CUDA_ERROR_ASSERT

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_TOO_MANY_PEERS

public static final int CUDA_ERROR_TOO_MANY_PEERS

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED

public static final int CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED

public static final int CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_HARDWARE_STACK_ERROR

public static final int CUDA_ERROR_HARDWARE_STACK_ERROR

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_ILLEGAL_INSTRUCTION

public static final int CUDA_ERROR_ILLEGAL_INSTRUCTION

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_MISALIGNED_ADDRESS

public static final int CUDA_ERROR_MISALIGNED_ADDRESS

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_INVALID_ADDRESS_SPACE

public static final int CUDA_ERROR_INVALID_ADDRESS_SPACE

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_INVALID_PC

public static final int CUDA_ERROR_INVALID_PC

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_LAUNCH_FAILED

public static final int CUDA_ERROR_LAUNCH_FAILED

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE

public static final int CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_NOT_PERMITTED

public static final int CUDA_ERROR_NOT_PERMITTED

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_NOT_SUPPORTED

public static final int CUDA_ERROR_NOT_SUPPORTED

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_SYSTEM_NOT_READY

public static final int CUDA_ERROR_SYSTEM_NOT_READY

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_SYSTEM_DRIVER_MISMATCH

public static final int CUDA_ERROR_SYSTEM_DRIVER_MISMATCH

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE

public static final int CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_MPS_CONNECTION_FAILED

public static final int CUDA_ERROR_MPS_CONNECTION_FAILED

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_MPS_RPC_FAILURE

public static final int CUDA_ERROR_MPS_RPC_FAILURE

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_MPS_SERVER_NOT_READY

public static final int CUDA_ERROR_MPS_SERVER_NOT_READY

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_MPS_MAX_CLIENTS_REACHED

public static final int CUDA_ERROR_MPS_MAX_CLIENTS_REACHED

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED

public static final int CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED

public static final int CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_STREAM_CAPTURE_INVALIDATED

public static final int CUDA_ERROR_STREAM_CAPTURE_INVALIDATED

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_STREAM_CAPTURE_MERGE

public static final int CUDA_ERROR_STREAM_CAPTURE_MERGE

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_STREAM_CAPTURE_UNMATCHED

public static final int CUDA_ERROR_STREAM_CAPTURE_UNMATCHED

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_STREAM_CAPTURE_UNJOINED

public static final int CUDA_ERROR_STREAM_CAPTURE_UNJOINED

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_STREAM_CAPTURE_ISOLATION

public static final int CUDA_ERROR_STREAM_CAPTURE_ISOLATION

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_STREAM_CAPTURE_IMPLICIT

public static final int CUDA_ERROR_STREAM_CAPTURE_IMPLICIT

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_CAPTURED_EVENT

public static final int CUDA_ERROR_CAPTURED_EVENT

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD

public static final int CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_TIMEOUT

public static final int CUDA_ERROR_TIMEOUT

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE

public static final int CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_EXTERNAL_DEVICE

public static final int CUDA_ERROR_EXTERNAL_DEVICE

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CUDA_ERROR_UNKNOWN

public static final int CUDA_ERROR_UNKNOWN

Error codes. (CUresult)

Enum values:

• CUDA_SUCCESS - The API call returned with no errors.

  In the case of query calls, this also means that the operation being queried is complete (see EventQuery and StreamQuery).

• CUDA_ERROR_INVALID_VALUE - This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.
• CUDA_ERROR_OUT_OF_MEMORY - The API call failed because it was unable to allocate enough memory to perform the requested operation.
• CUDA_ERROR_NOT_INITIALIZED - This indicates that the CUDA driver has not been initialized with Init or that initialization has failed.
• CUDA_ERROR_DEINITIALIZED - This indicates that the CUDA driver is in the process of shutting down.
• CUDA_ERROR_PROFILER_DISABLED - This indicates profiler is not initialized for this run. This can happen when the application is running with external profiling tools like visual profiler.
• CUDA_ERROR_PROFILER_NOT_INITIALIZED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to attempt to enable/disable the profiling via ProfilerStart or ProfilerStop without initialization.
• CUDA_ERROR_PROFILER_ALREADY_STARTED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStart when profiling is already enabled.
• CUDA_ERROR_PROFILER_ALREADY_STOPPED - Deprecated: This error return is deprecated as of CUDA 5.0. It is no longer an error to call ProfilerStop when profiling is already disabled.
• CUDA_ERROR_STUB_LIBRARY - This indicates that the CUDA driver that the application has loaded is a stub library. Applications that run with the stub rather than a real driver loaded will result in CUDA API returning this error.
• CUDA_ERROR_NO_DEVICE - This indicates that no CUDA-capable devices were detected by the installed CUDA driver.
• CUDA_ERROR_INVALID_DEVICE - This indicates that the device ordinal supplied by the user does not correspond to a valid CUDA device or that the action requested is invalid for the specified device.
• CUDA_ERROR_DEVICE_NOT_LICENSED - This error indicates that the Grid license is not applied.
• CUDA_ERROR_INVALID_IMAGE - This indicates that the device kernel image is invalid. This can also indicate an invalid CUDA module.
• CUDA_ERROR_INVALID_CONTEXT - This most frequently indicates that there is no context bound to the current thread. This can also be returned if the context passed to an API call is not a valid handle (such as a context that has had CtxDestroy invoked on it). This can also be returned if a user mixes different API versions (i.e. 3010 context with 3020 API calls). See CtxGetApiVersion for more details.
• CUDA_ERROR_CONTEXT_ALREADY_CURRENT - This indicated that the context being supplied as a parameter to the API call was already the active context.Deprecated: This error return is deprecated as of CUDA 3.2. It is no longer an error to attempt to push the active context via CtxPushCurrent.
• CUDA_ERROR_MAP_FAILED - This indicates that a map or register operation has failed.
• CUDA_ERROR_UNMAP_FAILED - This indicates that an unmap or unregister operation has failed.
• CUDA_ERROR_ARRAY_IS_MAPPED - This indicates that the specified array is currently mapped and thus cannot be destroyed.
• CUDA_ERROR_ALREADY_MAPPED - This indicates that the resource is already mapped.
• CUDA_ERROR_NO_BINARY_FOR_GPU - This indicates that there is no kernel image available that is suitable for the device. This can occur when a user specifies code generation options for a particular CUDA source file that do not include the corresponding device configuration.
• CUDA_ERROR_ALREADY_ACQUIRED - This indicates that a resource has already been acquired.
• CUDA_ERROR_NOT_MAPPED - This indicates that a resource is not mapped.
• CUDA_ERROR_NOT_MAPPED_AS_ARRAY - This indicates that a mapped resource is not available for access as an array.
• CUDA_ERROR_NOT_MAPPED_AS_POINTER - This indicates that a mapped resource is not available for access as a pointer.
• CUDA_ERROR_ECC_UNCORRECTABLE - This indicates that an uncorrectable ECC error was detected during execution.
• CUDA_ERROR_UNSUPPORTED_LIMIT - This indicates that the CUlimit passed to the API call is not supported by the active device.
• CUDA_ERROR_CONTEXT_ALREADY_IN_USE - This indicates that the CUcontext passed to the API call can only be bound to a single CPU thread at a time but is already bound to a CPU thread.
• CUDA_ERROR_PEER_ACCESS_UNSUPPORTED - This indicates that peer access is not supported across the given devices.
• CUDA_ERROR_INVALID_PTX - This indicates that a PTX JIT compilation failed.
• CUDA_ERROR_INVALID_GRAPHICS_CONTEXT - This indicates an error with OpenGL or DirectX context.
• CUDA_ERROR_NVLINK_UNCORRECTABLE - This indicates that an uncorrectable NVLink error was detected during the execution.
• CUDA_ERROR_JIT_COMPILER_NOT_FOUND - This indicates that the PTX JIT compiler library was not found.
• CUDA_ERROR_UNSUPPORTED_PTX_VERSION - This indicates that the provided PTX was compiled with an unsupported toolchain.
• CUDA_ERROR_JIT_COMPILATION_DISABLED - This indicates that the PTX JIT compilation was disabled.
• CUDA_ERROR_UNSUPPORTED_EXEC_AFFINITY - This indicates that the CUexecAffinityType passed to the API call is not supported by the active device.
• CUDA_ERROR_INVALID_SOURCE - This indicates that the device kernel source is invalid. This includes compilation/linker errors encountered in device code or user error.
• CUDA_ERROR_FILE_NOT_FOUND - This indicates that the file specified was not found.
• CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND - This indicates that a link to a shared object failed to resolve.
• CUDA_ERROR_SHARED_OBJECT_INIT_FAILED - This indicates that initialization of a shared object failed.
• CUDA_ERROR_OPERATING_SYSTEM - This indicates that an OS call failed.
• CUDA_ERROR_INVALID_HANDLE - This indicates that a resource handle passed to the API call was not valid. Resource handles are opaque types like CUstream and CUevent.
• CUDA_ERROR_ILLEGAL_STATE - This indicates that a resource required by the API call is not in a valid state to perform the requested operation.
• CUDA_ERROR_NOT_FOUND - This indicates that a named symbol was not found. Examples of symbols are global/constant variable names, driver function names, texture names, and surface names.
• CUDA_ERROR_NOT_READY - This indicates that asynchronous operations issued previously have not completed yet. This result is not actually an error, but must be indicated differently than CUDA_SUCCESS (which indicates completion). Calls that may return this value include EventQuery and StreamQuery.
• CUDA_ERROR_ILLEGAL_ADDRESS - While executing a kernel, the device encountered a load or store instruction on an invalid memory address. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES - This indicates that a launch did not occur because it did not have appropriate resources. This error usually indicates that the user has attempted to pass too many arguments to the device kernel, or the kernel launch specifies too many threads for the kernel's register count. Passing arguments of the wrong size (i.e. a 64-bit pointer when a 32-bit int is expected) is equivalent to passing too many arguments and can also result in this error.
• CUDA_ERROR_LAUNCH_TIMEOUT - This indicates that the device kernel took too long to execute. This can only occur if timeouts are enabled - see the device attribute DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING - This error indicates a kernel launch that uses an incompatible texturing mode.
• CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED - This error indicates that a call to CtxEnablePeerAccess is trying to re-enable peer access to a context which has already had peer access to it enabled.
• CUDA_ERROR_PEER_ACCESS_NOT_ENABLED - This error indicates that CtxDisablePeerAccess is trying to disable peer access which has not been enabled yet via CtxEnablePeerAccess.
• CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE - This error indicates that the primary context for the specified device has already been initialized.
• CUDA_ERROR_CONTEXT_IS_DESTROYED - This error indicates that the context current to the calling thread has been destroyed using CtxDestroy, or is a primary context which has not yet been initialized.
• CUDA_ERROR_ASSERT - A device-side assert triggered during kernel execution. The context cannot be used anymore, and must be destroyed. All existing device memory allocations from this context are invalid and must be reconstructed if the program is to continue using CUDA.
• CUDA_ERROR_TOO_MANY_PEERS - This error indicates that the hardware resources required to enable peer access have been exhausted for one or more of the devices passed to CtxEnablePeerAccess.
• CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED - This error indicates that the memory range passed to MemHostRegister has already been registered.
• CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED - This error indicates that the pointer passed to MemHostUnregister does not correspond to any currently registered memory region.
• CUDA_ERROR_HARDWARE_STACK_ERROR - While executing a kernel, the device encountered a stack error. This can be due to stack corruption or exceeding the stack size limit. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_ILLEGAL_INSTRUCTION - While executing a kernel, the device encountered an illegal instruction. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_MISALIGNED_ADDRESS - While executing a kernel, the device encountered a load or store instruction on a memory address which is not aligned. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_ADDRESS_SPACE - While executing a kernel, the device encountered an instruction which can only operate on memory locations in certain address spaces (global, shared, or local), but was supplied a memory address not belonging to an allowed address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_INVALID_PC - While executing a kernel, the device program counter wrapped its address space. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_LAUNCH_FAILED - An exception occurred on the device while executing a kernel. Common causes include dereferencing an invalid device pointer and accessing out of bounds shared memory. Less common cases can be system specific - more information about these cases can be found in the system specific user guide. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_COOPERATIVE_LAUNCH_TOO_LARGE - This error indicates that the number of blocks launched per grid for a kernel that was launched via either LaunchCooperativeKernel or LaunchCooperativeKernelMultiDevice exceeds the maximum number of blocks as allowed by OccupancyMaxActiveBlocksPerMultiprocessor or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.
• CUDA_ERROR_NOT_PERMITTED - This error indicates that the attempted operation is not permitted.
• CUDA_ERROR_NOT_SUPPORTED - This error indicates that the attempted operation is not supported on the current system or device.
• CUDA_ERROR_SYSTEM_NOT_READY - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH - This error indicates that there is a mismatch between the versions of the display driver and the CUDA driver. Refer to the compatibility documentation for supported versions.
• CUDA_ERROR_COMPAT_NOT_SUPPORTED_ON_DEVICE - This error indicates that the system was upgraded to run with forward compatibility but the visible hardware detected by CUDA does not support this configuration. Refer to the compatibility documentation for the supported hardware matrix or ensure that only supported hardware is visible during initialization via the CUDA_VISIBLE_DEVICES environment variable.
• CUDA_ERROR_MPS_CONNECTION_FAILED - This error indicates that the MPS client failed to connect to the MPS control daemon or the MPS server.
• CUDA_ERROR_MPS_RPC_FAILURE - This error indicates that the remote procedural call between the MPS server and the MPS client failed.
• CUDA_ERROR_MPS_SERVER_NOT_READY - This error indicates that the MPS server is not ready to accept new MPS client requests. This error can be returned when the MPS server is in the process of recovering from a fatal failure.
• CUDA_ERROR_MPS_MAX_CLIENTS_REACHED - This error indicates that the hardware resources required to create MPS client have been exhausted.
• CUDA_ERROR_MPS_MAX_CONNECTIONS_REACHED - This error indicates the the hardware resources required to support device connections have been exhausted.
• CUDA_ERROR_STREAM_CAPTURE_UNSUPPORTED - This error indicates that the operation is not permitted when the stream is capturing.
• CUDA_ERROR_STREAM_CAPTURE_INVALIDATED - This error indicates that the current capture sequence on the stream has been invalidated due to a previous error.
• CUDA_ERROR_STREAM_CAPTURE_MERGE - This error indicates that the operation would have resulted in a merge of two independent capture sequences.
• CUDA_ERROR_STREAM_CAPTURE_UNMATCHED - This error indicates that the capture was not initiated in this stream.
• CUDA_ERROR_STREAM_CAPTURE_UNJOINED - This error indicates that the capture sequence contains a fork that was not joined to the primary stream.
• CUDA_ERROR_STREAM_CAPTURE_ISOLATION - This error indicates that a dependency would have been created which crosses the capture sequence boundary. Only implicit in-stream ordering dependencies are allowed to cross the boundary.
• CUDA_ERROR_STREAM_CAPTURE_IMPLICIT - This error indicates a disallowed implicit dependency on a current capture sequence from cudaStreamLegacy.
• CUDA_ERROR_CAPTURED_EVENT - This error indicates that the operation is not permitted on an event which was last recorded in a capturing stream.
• CUDA_ERROR_STREAM_CAPTURE_WRONG_THREAD - A stream capture sequence not initiated with the STREAM_CAPTURE_MODE_RELAXED argument to StreamBeginCapture was passed to StreamEndCapture in a different thread.
• CUDA_ERROR_TIMEOUT - This error indicates that the timeout specified for the wait operation has lapsed.
• CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE - This error indicates that the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.
• CUDA_ERROR_EXTERNAL_DEVICE - This indicates that an async error has occurred in a device outside of CUDA. If CUDA was waiting for an external device's signal before consuming shared data, the external device signaled an error indicating that the data is not valid for consumption. This leaves the process in an inconsistent state and any further CUDA work will return the same error. To continue using CUDA, the process must be terminated and relaunched.
• CUDA_ERROR_UNKNOWN - This indicates that an unknown internal error has occurred.

See Also:

• Constant Field Values

CU_DEVICE_P2P_ATTRIBUTE_PERFORMANCE_RANK

public static final int CU_DEVICE_P2P_ATTRIBUTE_PERFORMANCE_RANK

P2P Attributes. (CUdevice_P2PAttribute)

Enum values:

• DEVICE_P2P_ATTRIBUTE_PERFORMANCE_RANK - A relative value indicating the performance of the link between two devices
• DEVICE_P2P_ATTRIBUTE_ACCESS_SUPPORTED - P2P Access is enable
• DEVICE_P2P_ATTRIBUTE_NATIVE_ATOMIC_SUPPORTED - Atomic operation over the link supported
• DEVICE_P2P_ATTRIBUTE_ACCESS_ACCESS_SUPPORTED - Deprecated, use CU_DEVICE_P2P_ATTRIBUTE_CUDA_ARRAY_ACCESS_SUPPORTED instead
• DEVICE_P2P_ATTRIBUTE_CUDA_ARRAY_ACCESS_SUPPORTED - Accessing CUDA arrays over the link supported

See Also:

• Constant Field Values

CU_DEVICE_P2P_ATTRIBUTE_ACCESS_SUPPORTED

public static final int CU_DEVICE_P2P_ATTRIBUTE_ACCESS_SUPPORTED

P2P Attributes. (CUdevice_P2PAttribute)

Enum values:

• DEVICE_P2P_ATTRIBUTE_PERFORMANCE_RANK - A relative value indicating the performance of the link between two devices
• DEVICE_P2P_ATTRIBUTE_ACCESS_SUPPORTED - P2P Access is enable
• DEVICE_P2P_ATTRIBUTE_NATIVE_ATOMIC_SUPPORTED - Atomic operation over the link supported
• DEVICE_P2P_ATTRIBUTE_ACCESS_ACCESS_SUPPORTED - Deprecated, use CU_DEVICE_P2P_ATTRIBUTE_CUDA_ARRAY_ACCESS_SUPPORTED instead
• DEVICE_P2P_ATTRIBUTE_CUDA_ARRAY_ACCESS_SUPPORTED - Accessing CUDA arrays over the link supported

See Also:

• Constant Field Values

CU_DEVICE_P2P_ATTRIBUTE_NATIVE_ATOMIC_SUPPORTED

public static final int CU_DEVICE_P2P_ATTRIBUTE_NATIVE_ATOMIC_SUPPORTED

P2P Attributes. (CUdevice_P2PAttribute)

Enum values:

• DEVICE_P2P_ATTRIBUTE_PERFORMANCE_RANK - A relative value indicating the performance of the link between two devices
• DEVICE_P2P_ATTRIBUTE_ACCESS_SUPPORTED - P2P Access is enable
• DEVICE_P2P_ATTRIBUTE_NATIVE_ATOMIC_SUPPORTED - Atomic operation over the link supported
• DEVICE_P2P_ATTRIBUTE_ACCESS_ACCESS_SUPPORTED - Deprecated, use CU_DEVICE_P2P_ATTRIBUTE_CUDA_ARRAY_ACCESS_SUPPORTED instead
• DEVICE_P2P_ATTRIBUTE_CUDA_ARRAY_ACCESS_SUPPORTED - Accessing CUDA arrays over the link supported

See Also:

• Constant Field Values

CU_DEVICE_P2P_ATTRIBUTE_ACCESS_ACCESS_SUPPORTED

public static final int CU_DEVICE_P2P_ATTRIBUTE_ACCESS_ACCESS_SUPPORTED

P2P Attributes. (CUdevice_P2PAttribute)

Enum values:

• DEVICE_P2P_ATTRIBUTE_PERFORMANCE_RANK - A relative value indicating the performance of the link between two devices
• DEVICE_P2P_ATTRIBUTE_ACCESS_SUPPORTED - P2P Access is enable
• DEVICE_P2P_ATTRIBUTE_NATIVE_ATOMIC_SUPPORTED - Atomic operation over the link supported
• DEVICE_P2P_ATTRIBUTE_ACCESS_ACCESS_SUPPORTED - Deprecated, use CU_DEVICE_P2P_ATTRIBUTE_CUDA_ARRAY_ACCESS_SUPPORTED instead
• DEVICE_P2P_ATTRIBUTE_CUDA_ARRAY_ACCESS_SUPPORTED - Accessing CUDA arrays over the link supported

See Also:

• Constant Field Values

CU_DEVICE_P2P_ATTRIBUTE_CUDA_ARRAY_ACCESS_SUPPORTED

public static final int CU_DEVICE_P2P_ATTRIBUTE_CUDA_ARRAY_ACCESS_SUPPORTED

P2P Attributes. (CUdevice_P2PAttribute)

Enum values:

• DEVICE_P2P_ATTRIBUTE_PERFORMANCE_RANK - A relative value indicating the performance of the link between two devices
• DEVICE_P2P_ATTRIBUTE_ACCESS_SUPPORTED - P2P Access is enable
• DEVICE_P2P_ATTRIBUTE_NATIVE_ATOMIC_SUPPORTED - Atomic operation over the link supported
• DEVICE_P2P_ATTRIBUTE_ACCESS_ACCESS_SUPPORTED - Deprecated, use CU_DEVICE_P2P_ATTRIBUTE_CUDA_ARRAY_ACCESS_SUPPORTED instead
• DEVICE_P2P_ATTRIBUTE_CUDA_ARRAY_ACCESS_SUPPORTED - Accessing CUDA arrays over the link supported

See Also:

• Constant Field Values

CU_MEMHOSTALLOC_PORTABLE

public static final int CU_MEMHOSTALLOC_PORTABLE

Flags for MemHostAlloc.

Enum values:

• MEMHOSTALLOC_PORTABLE - If set, host memory is portable between CUDA contexts.
• MEMHOSTALLOC_DEVICEMAP - If set, host memory is mapped into CUDA address space and MemHostGetDevicePointer may be called on the host pointer.
• MEMHOSTALLOC_WRITECOMBINED - If set, host memory is allocated as write-combined - fast to write, faster to DMA, slow to read except via SSE4 streaming load instruction (MOVNTDQA).

See Also:

• Constant Field Values

CU_MEMHOSTALLOC_DEVICEMAP

public static final int CU_MEMHOSTALLOC_DEVICEMAP

Flags for MemHostAlloc.

Enum values:

• MEMHOSTALLOC_PORTABLE - If set, host memory is portable between CUDA contexts.
• MEMHOSTALLOC_DEVICEMAP - If set, host memory is mapped into CUDA address space and MemHostGetDevicePointer may be called on the host pointer.
• MEMHOSTALLOC_WRITECOMBINED - If set, host memory is allocated as write-combined - fast to write, faster to DMA, slow to read except via SSE4 streaming load instruction (MOVNTDQA).

See Also:

• Constant Field Values

CU_MEMHOSTALLOC_WRITECOMBINED

public static final int CU_MEMHOSTALLOC_WRITECOMBINED

Flags for MemHostAlloc.

Enum values:

• MEMHOSTALLOC_PORTABLE - If set, host memory is portable between CUDA contexts.
• MEMHOSTALLOC_DEVICEMAP - If set, host memory is mapped into CUDA address space and MemHostGetDevicePointer may be called on the host pointer.
• MEMHOSTALLOC_WRITECOMBINED - If set, host memory is allocated as write-combined - fast to write, faster to DMA, slow to read except via SSE4 streaming load instruction (MOVNTDQA).

See Also:

• Constant Field Values

CU_MEMHOSTREGISTER_PORTABLE

public static final int CU_MEMHOSTREGISTER_PORTABLE

Flags for MemHostRegister.

Enum values:

• MEMHOSTREGISTER_PORTABLE - If set, host memory is portable between CUDA contexts.
• MEMHOSTREGISTER_DEVICEMAP - If set, host memory is mapped into CUDA address space and MemHostGetDevicePointer may be called on the host pointer.
• MEMHOSTREGISTER_IOMEMORY - If set, the passed memory pointer is treated as pointing to some memory-mapped I/O space, e.g. belonging to a third-party PCIe device.

  On Windows the flag is a no-op. On Linux that memory is marked as non cache-coherent for the GPU and is expected to be physically contiguous. It may return CUDA_ERROR_NOT_PERMITTED if run as an unprivileged user, CUDA_ERROR_NOT_SUPPORTED on older Linux kernel versions. On all other platforms, it is not supported and CUDA_ERROR_NOT_SUPPORTED is returned.

• MEMHOSTREGISTER_READ_ONLY - If set, the passed memory pointer is treated as pointing to memory that is considered read-only by the device.

  On platforms without DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES, this flag is required in order to register memory mapped to the CPU as read-only. Support for the use of this flag can be queried from the device attribute DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED. Using this flag with a current context associated with a device that does not have this attribute set will cause MemHostRegister to error with CUDA_ERROR_NOT_SUPPORTED.

See Also:

• Constant Field Values

CU_MEMHOSTREGISTER_DEVICEMAP

public static final int CU_MEMHOSTREGISTER_DEVICEMAP

Flags for MemHostRegister.

Enum values:

• MEMHOSTREGISTER_PORTABLE - If set, host memory is portable between CUDA contexts.
• MEMHOSTREGISTER_DEVICEMAP - If set, host memory is mapped into CUDA address space and MemHostGetDevicePointer may be called on the host pointer.
• MEMHOSTREGISTER_IOMEMORY - If set, the passed memory pointer is treated as pointing to some memory-mapped I/O space, e.g. belonging to a third-party PCIe device.

  On Windows the flag is a no-op. On Linux that memory is marked as non cache-coherent for the GPU and is expected to be physically contiguous. It may return CUDA_ERROR_NOT_PERMITTED if run as an unprivileged user, CUDA_ERROR_NOT_SUPPORTED on older Linux kernel versions. On all other platforms, it is not supported and CUDA_ERROR_NOT_SUPPORTED is returned.

• MEMHOSTREGISTER_READ_ONLY - If set, the passed memory pointer is treated as pointing to memory that is considered read-only by the device.

  On platforms without DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES, this flag is required in order to register memory mapped to the CPU as read-only. Support for the use of this flag can be queried from the device attribute DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED. Using this flag with a current context associated with a device that does not have this attribute set will cause MemHostRegister to error with CUDA_ERROR_NOT_SUPPORTED.

See Also:

• Constant Field Values

CU_MEMHOSTREGISTER_IOMEMORY

public static final int CU_MEMHOSTREGISTER_IOMEMORY

Flags for MemHostRegister.

Enum values:

• MEMHOSTREGISTER_PORTABLE - If set, host memory is portable between CUDA contexts.
• MEMHOSTREGISTER_DEVICEMAP - If set, host memory is mapped into CUDA address space and MemHostGetDevicePointer may be called on the host pointer.
• MEMHOSTREGISTER_IOMEMORY - If set, the passed memory pointer is treated as pointing to some memory-mapped I/O space, e.g. belonging to a third-party PCIe device.

  On Windows the flag is a no-op. On Linux that memory is marked as non cache-coherent for the GPU and is expected to be physically contiguous. It may return CUDA_ERROR_NOT_PERMITTED if run as an unprivileged user, CUDA_ERROR_NOT_SUPPORTED on older Linux kernel versions. On all other platforms, it is not supported and CUDA_ERROR_NOT_SUPPORTED is returned.

• MEMHOSTREGISTER_READ_ONLY - If set, the passed memory pointer is treated as pointing to memory that is considered read-only by the device.

  On platforms without DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES, this flag is required in order to register memory mapped to the CPU as read-only. Support for the use of this flag can be queried from the device attribute DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED. Using this flag with a current context associated with a device that does not have this attribute set will cause MemHostRegister to error with CUDA_ERROR_NOT_SUPPORTED.

See Also:

• Constant Field Values

CU_MEMHOSTREGISTER_READ_ONLY

public static final int CU_MEMHOSTREGISTER_READ_ONLY

Flags for MemHostRegister.

Enum values:

• MEMHOSTREGISTER_PORTABLE - If set, host memory is portable between CUDA contexts.
• MEMHOSTREGISTER_DEVICEMAP - If set, host memory is mapped into CUDA address space and MemHostGetDevicePointer may be called on the host pointer.
• MEMHOSTREGISTER_IOMEMORY - If set, the passed memory pointer is treated as pointing to some memory-mapped I/O space, e.g. belonging to a third-party PCIe device.

  On Windows the flag is a no-op. On Linux that memory is marked as non cache-coherent for the GPU and is expected to be physically contiguous. It may return CUDA_ERROR_NOT_PERMITTED if run as an unprivileged user, CUDA_ERROR_NOT_SUPPORTED on older Linux kernel versions. On all other platforms, it is not supported and CUDA_ERROR_NOT_SUPPORTED is returned.

• MEMHOSTREGISTER_READ_ONLY - If set, the passed memory pointer is treated as pointing to memory that is considered read-only by the device.

  On platforms without DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES, this flag is required in order to register memory mapped to the CPU as read-only. Support for the use of this flag can be queried from the device attribute DEVICE_ATTRIBUTE_READ_ONLY_HOST_REGISTER_SUPPORTED. Using this flag with a current context associated with a device that does not have this attribute set will cause MemHostRegister to error with CUDA_ERROR_NOT_SUPPORTED.

See Also:

• Constant Field Values

CU_ARRAY_SPARSE_PROPERTIES_SINGLE_MIPTAIL

public static final int CU_ARRAY_SPARSE_PROPERTIES_SINGLE_MIPTAIL

Indicates that the layered sparse CUDA array or CUDA mipmapped array has a single mip tail region for all layers.

See Also:

• Constant Field Values

CU_RES_VIEW_FORMAT_NONE

public static final int CU_RES_VIEW_FORMAT_NONE

Resource view format. (CUresourceViewFormat)

Enum values:

• RES_VIEW_FORMAT_NONE - No resource view format (use underlying resource format)
• RES_VIEW_FORMAT_UINT_1X8 - 1 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_UINT_2X8 - 2 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_UINT_4X8 - 4 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_SINT_1X8 - 1 channel signed 8-bit integers
• RES_VIEW_FORMAT_SINT_2X8 - 2 channel signed 8-bit integers
• RES_VIEW_FORMAT_SINT_4X8 - 4 channel signed 8-bit integers
• RES_VIEW_FORMAT_UINT_1X16 - 1 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_UINT_2X16 - 2 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_UINT_4X16 - 4 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_SINT_1X16 - 1 channel signed 16-bit integers
• RES_VIEW_FORMAT_SINT_2X16 - 2 channel signed 16-bit integers
• RES_VIEW_FORMAT_SINT_4X16 - 4 channel signed 16-bit integers
• RES_VIEW_FORMAT_UINT_1X32 - 1 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_UINT_2X32 - 2 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_UINT_4X32 - 4 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_SINT_1X32 - 1 channel signed 32-bit integers
• RES_VIEW_FORMAT_SINT_2X32 - 2 channel signed 32-bit integers
• RES_VIEW_FORMAT_SINT_4X32 - 4 channel signed 32-bit integers
• RES_VIEW_FORMAT_FLOAT_1X16 - 1 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_2X16 - 2 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_4X16 - 4 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_1X32 - 1 channel 32-bit floating point
• RES_VIEW_FORMAT_FLOAT_2X32 - 2 channel 32-bit floating point
• RES_VIEW_FORMAT_FLOAT_4X32 - 4 channel 32-bit floating point
• RES_VIEW_FORMAT_UNSIGNED_BC1 - Block compressed 1
• RES_VIEW_FORMAT_UNSIGNED_BC2 - Block compressed 2
• RES_VIEW_FORMAT_UNSIGNED_BC3 - Block compressed 3
• RES_VIEW_FORMAT_UNSIGNED_BC4 - Block compressed 4 unsigned
• RES_VIEW_FORMAT_SIGNED_BC4 - Block compressed 4 signed
• RES_VIEW_FORMAT_UNSIGNED_BC5 - Block compressed 5 unsigned
• RES_VIEW_FORMAT_SIGNED_BC5 - Block compressed 5 signed
• RES_VIEW_FORMAT_UNSIGNED_BC6H - Block compressed 6 unsigned half-float
• RES_VIEW_FORMAT_SIGNED_BC6H - Block compressed 6 signed half-float
• RES_VIEW_FORMAT_UNSIGNED_BC7 - Block compressed 7

See Also:

• Constant Field Values

CU_RES_VIEW_FORMAT_UINT_1X8

public static final int CU_RES_VIEW_FORMAT_UINT_1X8

Resource view format. (CUresourceViewFormat)

Enum values:

• RES_VIEW_FORMAT_NONE - No resource view format (use underlying resource format)
• RES_VIEW_FORMAT_UINT_1X8 - 1 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_UINT_2X8 - 2 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_UINT_4X8 - 4 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_SINT_1X8 - 1 channel signed 8-bit integers
• RES_VIEW_FORMAT_SINT_2X8 - 2 channel signed 8-bit integers
• RES_VIEW_FORMAT_SINT_4X8 - 4 channel signed 8-bit integers
• RES_VIEW_FORMAT_UINT_1X16 - 1 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_UINT_2X16 - 2 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_UINT_4X16 - 4 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_SINT_1X16 - 1 channel signed 16-bit integers
• RES_VIEW_FORMAT_SINT_2X16 - 2 channel signed 16-bit integers
• RES_VIEW_FORMAT_SINT_4X16 - 4 channel signed 16-bit integers
• RES_VIEW_FORMAT_UINT_1X32 - 1 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_UINT_2X32 - 2 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_UINT_4X32 - 4 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_SINT_1X32 - 1 channel signed 32-bit integers
• RES_VIEW_FORMAT_SINT_2X32 - 2 channel signed 32-bit integers
• RES_VIEW_FORMAT_SINT_4X32 - 4 channel signed 32-bit integers
• RES_VIEW_FORMAT_FLOAT_1X16 - 1 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_2X16 - 2 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_4X16 - 4 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_1X32 - 1 channel 32-bit floating point
• RES_VIEW_FORMAT_FLOAT_2X32 - 2 channel 32-bit floating point
• RES_VIEW_FORMAT_FLOAT_4X32 - 4 channel 32-bit floating point
• RES_VIEW_FORMAT_UNSIGNED_BC1 - Block compressed 1
• RES_VIEW_FORMAT_UNSIGNED_BC2 - Block compressed 2
• RES_VIEW_FORMAT_UNSIGNED_BC3 - Block compressed 3
• RES_VIEW_FORMAT_UNSIGNED_BC4 - Block compressed 4 unsigned
• RES_VIEW_FORMAT_SIGNED_BC4 - Block compressed 4 signed
• RES_VIEW_FORMAT_UNSIGNED_BC5 - Block compressed 5 unsigned
• RES_VIEW_FORMAT_SIGNED_BC5 - Block compressed 5 signed
• RES_VIEW_FORMAT_UNSIGNED_BC6H - Block compressed 6 unsigned half-float
• RES_VIEW_FORMAT_SIGNED_BC6H - Block compressed 6 signed half-float
• RES_VIEW_FORMAT_UNSIGNED_BC7 - Block compressed 7

See Also:

• Constant Field Values

CU_RES_VIEW_FORMAT_UINT_2X8

public static final int CU_RES_VIEW_FORMAT_UINT_2X8

Resource view format. (CUresourceViewFormat)

Enum values:

• RES_VIEW_FORMAT_NONE - No resource view format (use underlying resource format)
• RES_VIEW_FORMAT_UINT_1X8 - 1 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_UINT_2X8 - 2 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_UINT_4X8 - 4 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_SINT_1X8 - 1 channel signed 8-bit integers
• RES_VIEW_FORMAT_SINT_2X8 - 2 channel signed 8-bit integers
• RES_VIEW_FORMAT_SINT_4X8 - 4 channel signed 8-bit integers
• RES_VIEW_FORMAT_UINT_1X16 - 1 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_UINT_2X16 - 2 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_UINT_4X16 - 4 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_SINT_1X16 - 1 channel signed 16-bit integers
• RES_VIEW_FORMAT_SINT_2X16 - 2 channel signed 16-bit integers
• RES_VIEW_FORMAT_SINT_4X16 - 4 channel signed 16-bit integers
• RES_VIEW_FORMAT_UINT_1X32 - 1 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_UINT_2X32 - 2 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_UINT_4X32 - 4 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_SINT_1X32 - 1 channel signed 32-bit integers
• RES_VIEW_FORMAT_SINT_2X32 - 2 channel signed 32-bit integers
• RES_VIEW_FORMAT_SINT_4X32 - 4 channel signed 32-bit integers
• RES_VIEW_FORMAT_FLOAT_1X16 - 1 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_2X16 - 2 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_4X16 - 4 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_1X32 - 1 channel 32-bit floating point
• RES_VIEW_FORMAT_FLOAT_2X32 - 2 channel 32-bit floating point
• RES_VIEW_FORMAT_FLOAT_4X32 - 4 channel 32-bit floating point
• RES_VIEW_FORMAT_UNSIGNED_BC1 - Block compressed 1
• RES_VIEW_FORMAT_UNSIGNED_BC2 - Block compressed 2
• RES_VIEW_FORMAT_UNSIGNED_BC3 - Block compressed 3
• RES_VIEW_FORMAT_UNSIGNED_BC4 - Block compressed 4 unsigned
• RES_VIEW_FORMAT_SIGNED_BC4 - Block compressed 4 signed
• RES_VIEW_FORMAT_UNSIGNED_BC5 - Block compressed 5 unsigned
• RES_VIEW_FORMAT_SIGNED_BC5 - Block compressed 5 signed
• RES_VIEW_FORMAT_UNSIGNED_BC6H - Block compressed 6 unsigned half-float
• RES_VIEW_FORMAT_SIGNED_BC6H - Block compressed 6 signed half-float
• RES_VIEW_FORMAT_UNSIGNED_BC7 - Block compressed 7

See Also:

• Constant Field Values

CU_RES_VIEW_FORMAT_UINT_4X8

public static final int CU_RES_VIEW_FORMAT_UINT_4X8

Resource view format. (CUresourceViewFormat)

Enum values:

• RES_VIEW_FORMAT_NONE - No resource view format (use underlying resource format)
• RES_VIEW_FORMAT_UINT_1X8 - 1 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_UINT_2X8 - 2 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_UINT_4X8 - 4 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_SINT_1X8 - 1 channel signed 8-bit integers
• RES_VIEW_FORMAT_SINT_2X8 - 2 channel signed 8-bit integers
• RES_VIEW_FORMAT_SINT_4X8 - 4 channel signed 8-bit integers
• RES_VIEW_FORMAT_UINT_1X16 - 1 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_UINT_2X16 - 2 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_UINT_4X16 - 4 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_SINT_1X16 - 1 channel signed 16-bit integers
• RES_VIEW_FORMAT_SINT_2X16 - 2 channel signed 16-bit integers
• RES_VIEW_FORMAT_SINT_4X16 - 4 channel signed 16-bit integers
• RES_VIEW_FORMAT_UINT_1X32 - 1 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_UINT_2X32 - 2 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_UINT_4X32 - 4 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_SINT_1X32 - 1 channel signed 32-bit integers
• RES_VIEW_FORMAT_SINT_2X32 - 2 channel signed 32-bit integers
• RES_VIEW_FORMAT_SINT_4X32 - 4 channel signed 32-bit integers
• RES_VIEW_FORMAT_FLOAT_1X16 - 1 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_2X16 - 2 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_4X16 - 4 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_1X32 - 1 channel 32-bit floating point
• RES_VIEW_FORMAT_FLOAT_2X32 - 2 channel 32-bit floating point
• RES_VIEW_FORMAT_FLOAT_4X32 - 4 channel 32-bit floating point
• RES_VIEW_FORMAT_UNSIGNED_BC1 - Block compressed 1
• RES_VIEW_FORMAT_UNSIGNED_BC2 - Block compressed 2
• RES_VIEW_FORMAT_UNSIGNED_BC3 - Block compressed 3
• RES_VIEW_FORMAT_UNSIGNED_BC4 - Block compressed 4 unsigned
• RES_VIEW_FORMAT_SIGNED_BC4 - Block compressed 4 signed
• RES_VIEW_FORMAT_UNSIGNED_BC5 - Block compressed 5 unsigned
• RES_VIEW_FORMAT_SIGNED_BC5 - Block compressed 5 signed
• RES_VIEW_FORMAT_UNSIGNED_BC6H - Block compressed 6 unsigned half-float
• RES_VIEW_FORMAT_SIGNED_BC6H - Block compressed 6 signed half-float
• RES_VIEW_FORMAT_UNSIGNED_BC7 - Block compressed 7

See Also:

• Constant Field Values

CU_RES_VIEW_FORMAT_SINT_1X8

public static final int CU_RES_VIEW_FORMAT_SINT_1X8

Resource view format. (CUresourceViewFormat)

Enum values:

• RES_VIEW_FORMAT_NONE - No resource view format (use underlying resource format)
• RES_VIEW_FORMAT_UINT_1X8 - 1 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_UINT_2X8 - 2 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_UINT_4X8 - 4 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_SINT_1X8 - 1 channel signed 8-bit integers
• RES_VIEW_FORMAT_SINT_2X8 - 2 channel signed 8-bit integers
• RES_VIEW_FORMAT_SINT_4X8 - 4 channel signed 8-bit integers
• RES_VIEW_FORMAT_UINT_1X16 - 1 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_UINT_2X16 - 2 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_UINT_4X16 - 4 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_SINT_1X16 - 1 channel signed 16-bit integers
• RES_VIEW_FORMAT_SINT_2X16 - 2 channel signed 16-bit integers
• RES_VIEW_FORMAT_SINT_4X16 - 4 channel signed 16-bit integers
• RES_VIEW_FORMAT_UINT_1X32 - 1 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_UINT_2X32 - 2 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_UINT_4X32 - 4 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_SINT_1X32 - 1 channel signed 32-bit integers
• RES_VIEW_FORMAT_SINT_2X32 - 2 channel signed 32-bit integers
• RES_VIEW_FORMAT_SINT_4X32 - 4 channel signed 32-bit integers
• RES_VIEW_FORMAT_FLOAT_1X16 - 1 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_2X16 - 2 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_4X16 - 4 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_1X32 - 1 channel 32-bit floating point
• RES_VIEW_FORMAT_FLOAT_2X32 - 2 channel 32-bit floating point
• RES_VIEW_FORMAT_FLOAT_4X32 - 4 channel 32-bit floating point
• RES_VIEW_FORMAT_UNSIGNED_BC1 - Block compressed 1
• RES_VIEW_FORMAT_UNSIGNED_BC2 - Block compressed 2
• RES_VIEW_FORMAT_UNSIGNED_BC3 - Block compressed 3
• RES_VIEW_FORMAT_UNSIGNED_BC4 - Block compressed 4 unsigned
• RES_VIEW_FORMAT_SIGNED_BC4 - Block compressed 4 signed
• RES_VIEW_FORMAT_UNSIGNED_BC5 - Block compressed 5 unsigned
• RES_VIEW_FORMAT_SIGNED_BC5 - Block compressed 5 signed
• RES_VIEW_FORMAT_UNSIGNED_BC6H - Block compressed 6 unsigned half-float
• RES_VIEW_FORMAT_SIGNED_BC6H - Block compressed 6 signed half-float
• RES_VIEW_FORMAT_UNSIGNED_BC7 - Block compressed 7

See Also:

• Constant Field Values

CU_RES_VIEW_FORMAT_SINT_2X8

public static final int CU_RES_VIEW_FORMAT_SINT_2X8

Resource view format. (CUresourceViewFormat)

Enum values:

• RES_VIEW_FORMAT_NONE - No resource view format (use underlying resource format)
• RES_VIEW_FORMAT_UINT_1X8 - 1 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_UINT_2X8 - 2 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_UINT_4X8 - 4 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_SINT_1X8 - 1 channel signed 8-bit integers
• RES_VIEW_FORMAT_SINT_2X8 - 2 channel signed 8-bit integers
• RES_VIEW_FORMAT_SINT_4X8 - 4 channel signed 8-bit integers
• RES_VIEW_FORMAT_UINT_1X16 - 1 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_UINT_2X16 - 2 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_UINT_4X16 - 4 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_SINT_1X16 - 1 channel signed 16-bit integers
• RES_VIEW_FORMAT_SINT_2X16 - 2 channel signed 16-bit integers
• RES_VIEW_FORMAT_SINT_4X16 - 4 channel signed 16-bit integers
• RES_VIEW_FORMAT_UINT_1X32 - 1 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_UINT_2X32 - 2 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_UINT_4X32 - 4 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_SINT_1X32 - 1 channel signed 32-bit integers
• RES_VIEW_FORMAT_SINT_2X32 - 2 channel signed 32-bit integers
• RES_VIEW_FORMAT_SINT_4X32 - 4 channel signed 32-bit integers
• RES_VIEW_FORMAT_FLOAT_1X16 - 1 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_2X16 - 2 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_4X16 - 4 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_1X32 - 1 channel 32-bit floating point
• RES_VIEW_FORMAT_FLOAT_2X32 - 2 channel 32-bit floating point
• RES_VIEW_FORMAT_FLOAT_4X32 - 4 channel 32-bit floating point
• RES_VIEW_FORMAT_UNSIGNED_BC1 - Block compressed 1
• RES_VIEW_FORMAT_UNSIGNED_BC2 - Block compressed 2
• RES_VIEW_FORMAT_UNSIGNED_BC3 - Block compressed 3
• RES_VIEW_FORMAT_UNSIGNED_BC4 - Block compressed 4 unsigned
• RES_VIEW_FORMAT_SIGNED_BC4 - Block compressed 4 signed
• RES_VIEW_FORMAT_UNSIGNED_BC5 - Block compressed 5 unsigned
• RES_VIEW_FORMAT_SIGNED_BC5 - Block compressed 5 signed
• RES_VIEW_FORMAT_UNSIGNED_BC6H - Block compressed 6 unsigned half-float
• RES_VIEW_FORMAT_SIGNED_BC6H - Block compressed 6 signed half-float
• RES_VIEW_FORMAT_UNSIGNED_BC7 - Block compressed 7

See Also:

• Constant Field Values

CU_RES_VIEW_FORMAT_SINT_4X8

public static final int CU_RES_VIEW_FORMAT_SINT_4X8

Resource view format. (CUresourceViewFormat)

Enum values:

• RES_VIEW_FORMAT_NONE - No resource view format (use underlying resource format)
• RES_VIEW_FORMAT_UINT_1X8 - 1 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_UINT_2X8 - 2 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_UINT_4X8 - 4 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_SINT_1X8 - 1 channel signed 8-bit integers
• RES_VIEW_FORMAT_SINT_2X8 - 2 channel signed 8-bit integers
• RES_VIEW_FORMAT_SINT_4X8 - 4 channel signed 8-bit integers
• RES_VIEW_FORMAT_UINT_1X16 - 1 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_UINT_2X16 - 2 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_UINT_4X16 - 4 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_SINT_1X16 - 1 channel signed 16-bit integers
• RES_VIEW_FORMAT_SINT_2X16 - 2 channel signed 16-bit integers
• RES_VIEW_FORMAT_SINT_4X16 - 4 channel signed 16-bit integers
• RES_VIEW_FORMAT_UINT_1X32 - 1 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_UINT_2X32 - 2 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_UINT_4X32 - 4 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_SINT_1X32 - 1 channel signed 32-bit integers
• RES_VIEW_FORMAT_SINT_2X32 - 2 channel signed 32-bit integers
• RES_VIEW_FORMAT_SINT_4X32 - 4 channel signed 32-bit integers
• RES_VIEW_FORMAT_FLOAT_1X16 - 1 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_2X16 - 2 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_4X16 - 4 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_1X32 - 1 channel 32-bit floating point
• RES_VIEW_FORMAT_FLOAT_2X32 - 2 channel 32-bit floating point
• RES_VIEW_FORMAT_FLOAT_4X32 - 4 channel 32-bit floating point
• RES_VIEW_FORMAT_UNSIGNED_BC1 - Block compressed 1
• RES_VIEW_FORMAT_UNSIGNED_BC2 - Block compressed 2
• RES_VIEW_FORMAT_UNSIGNED_BC3 - Block compressed 3
• RES_VIEW_FORMAT_UNSIGNED_BC4 - Block compressed 4 unsigned
• RES_VIEW_FORMAT_SIGNED_BC4 - Block compressed 4 signed
• RES_VIEW_FORMAT_UNSIGNED_BC5 - Block compressed 5 unsigned
• RES_VIEW_FORMAT_SIGNED_BC5 - Block compressed 5 signed
• RES_VIEW_FORMAT_UNSIGNED_BC6H - Block compressed 6 unsigned half-float
• RES_VIEW_FORMAT_SIGNED_BC6H - Block compressed 6 signed half-float
• RES_VIEW_FORMAT_UNSIGNED_BC7 - Block compressed 7

See Also:

• Constant Field Values

CU_RES_VIEW_FORMAT_UINT_1X16

public static final int CU_RES_VIEW_FORMAT_UINT_1X16

Resource view format. (CUresourceViewFormat)

Enum values:

• RES_VIEW_FORMAT_NONE - No resource view format (use underlying resource format)
• RES_VIEW_FORMAT_UINT_1X8 - 1 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_UINT_2X8 - 2 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_UINT_4X8 - 4 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_SINT_1X8 - 1 channel signed 8-bit integers
• RES_VIEW_FORMAT_SINT_2X8 - 2 channel signed 8-bit integers
• RES_VIEW_FORMAT_SINT_4X8 - 4 channel signed 8-bit integers
• RES_VIEW_FORMAT_UINT_1X16 - 1 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_UINT_2X16 - 2 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_UINT_4X16 - 4 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_SINT_1X16 - 1 channel signed 16-bit integers
• RES_VIEW_FORMAT_SINT_2X16 - 2 channel signed 16-bit integers
• RES_VIEW_FORMAT_SINT_4X16 - 4 channel signed 16-bit integers
• RES_VIEW_FORMAT_UINT_1X32 - 1 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_UINT_2X32 - 2 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_UINT_4X32 - 4 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_SINT_1X32 - 1 channel signed 32-bit integers
• RES_VIEW_FORMAT_SINT_2X32 - 2 channel signed 32-bit integers
• RES_VIEW_FORMAT_SINT_4X32 - 4 channel signed 32-bit integers
• RES_VIEW_FORMAT_FLOAT_1X16 - 1 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_2X16 - 2 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_4X16 - 4 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_1X32 - 1 channel 32-bit floating point
• RES_VIEW_FORMAT_FLOAT_2X32 - 2 channel 32-bit floating point
• RES_VIEW_FORMAT_FLOAT_4X32 - 4 channel 32-bit floating point
• RES_VIEW_FORMAT_UNSIGNED_BC1 - Block compressed 1
• RES_VIEW_FORMAT_UNSIGNED_BC2 - Block compressed 2
• RES_VIEW_FORMAT_UNSIGNED_BC3 - Block compressed 3
• RES_VIEW_FORMAT_UNSIGNED_BC4 - Block compressed 4 unsigned
• RES_VIEW_FORMAT_SIGNED_BC4 - Block compressed 4 signed
• RES_VIEW_FORMAT_UNSIGNED_BC5 - Block compressed 5 unsigned
• RES_VIEW_FORMAT_SIGNED_BC5 - Block compressed 5 signed
• RES_VIEW_FORMAT_UNSIGNED_BC6H - Block compressed 6 unsigned half-float
• RES_VIEW_FORMAT_SIGNED_BC6H - Block compressed 6 signed half-float
• RES_VIEW_FORMAT_UNSIGNED_BC7 - Block compressed 7

See Also:

• Constant Field Values

CU_RES_VIEW_FORMAT_UINT_2X16

public static final int CU_RES_VIEW_FORMAT_UINT_2X16

Resource view format. (CUresourceViewFormat)

Enum values:

• RES_VIEW_FORMAT_NONE - No resource view format (use underlying resource format)
• RES_VIEW_FORMAT_UINT_1X8 - 1 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_UINT_2X8 - 2 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_UINT_4X8 - 4 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_SINT_1X8 - 1 channel signed 8-bit integers
• RES_VIEW_FORMAT_SINT_2X8 - 2 channel signed 8-bit integers
• RES_VIEW_FORMAT_SINT_4X8 - 4 channel signed 8-bit integers
• RES_VIEW_FORMAT_UINT_1X16 - 1 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_UINT_2X16 - 2 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_UINT_4X16 - 4 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_SINT_1X16 - 1 channel signed 16-bit integers
• RES_VIEW_FORMAT_SINT_2X16 - 2 channel signed 16-bit integers
• RES_VIEW_FORMAT_SINT_4X16 - 4 channel signed 16-bit integers
• RES_VIEW_FORMAT_UINT_1X32 - 1 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_UINT_2X32 - 2 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_UINT_4X32 - 4 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_SINT_1X32 - 1 channel signed 32-bit integers
• RES_VIEW_FORMAT_SINT_2X32 - 2 channel signed 32-bit integers
• RES_VIEW_FORMAT_SINT_4X32 - 4 channel signed 32-bit integers
• RES_VIEW_FORMAT_FLOAT_1X16 - 1 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_2X16 - 2 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_4X16 - 4 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_1X32 - 1 channel 32-bit floating point
• RES_VIEW_FORMAT_FLOAT_2X32 - 2 channel 32-bit floating point
• RES_VIEW_FORMAT_FLOAT_4X32 - 4 channel 32-bit floating point
• RES_VIEW_FORMAT_UNSIGNED_BC1 - Block compressed 1
• RES_VIEW_FORMAT_UNSIGNED_BC2 - Block compressed 2
• RES_VIEW_FORMAT_UNSIGNED_BC3 - Block compressed 3
• RES_VIEW_FORMAT_UNSIGNED_BC4 - Block compressed 4 unsigned
• RES_VIEW_FORMAT_SIGNED_BC4 - Block compressed 4 signed
• RES_VIEW_FORMAT_UNSIGNED_BC5 - Block compressed 5 unsigned
• RES_VIEW_FORMAT_SIGNED_BC5 - Block compressed 5 signed
• RES_VIEW_FORMAT_UNSIGNED_BC6H - Block compressed 6 unsigned half-float
• RES_VIEW_FORMAT_SIGNED_BC6H - Block compressed 6 signed half-float
• RES_VIEW_FORMAT_UNSIGNED_BC7 - Block compressed 7

See Also:

• Constant Field Values

CU_RES_VIEW_FORMAT_UINT_4X16

public static final int CU_RES_VIEW_FORMAT_UINT_4X16

Resource view format. (CUresourceViewFormat)

Enum values:

• RES_VIEW_FORMAT_NONE - No resource view format (use underlying resource format)
• RES_VIEW_FORMAT_UINT_1X8 - 1 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_UINT_2X8 - 2 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_UINT_4X8 - 4 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_SINT_1X8 - 1 channel signed 8-bit integers
• RES_VIEW_FORMAT_SINT_2X8 - 2 channel signed 8-bit integers
• RES_VIEW_FORMAT_SINT_4X8 - 4 channel signed 8-bit integers
• RES_VIEW_FORMAT_UINT_1X16 - 1 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_UINT_2X16 - 2 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_UINT_4X16 - 4 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_SINT_1X16 - 1 channel signed 16-bit integers
• RES_VIEW_FORMAT_SINT_2X16 - 2 channel signed 16-bit integers
• RES_VIEW_FORMAT_SINT_4X16 - 4 channel signed 16-bit integers
• RES_VIEW_FORMAT_UINT_1X32 - 1 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_UINT_2X32 - 2 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_UINT_4X32 - 4 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_SINT_1X32 - 1 channel signed 32-bit integers
• RES_VIEW_FORMAT_SINT_2X32 - 2 channel signed 32-bit integers
• RES_VIEW_FORMAT_SINT_4X32 - 4 channel signed 32-bit integers
• RES_VIEW_FORMAT_FLOAT_1X16 - 1 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_2X16 - 2 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_4X16 - 4 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_1X32 - 1 channel 32-bit floating point
• RES_VIEW_FORMAT_FLOAT_2X32 - 2 channel 32-bit floating point
• RES_VIEW_FORMAT_FLOAT_4X32 - 4 channel 32-bit floating point
• RES_VIEW_FORMAT_UNSIGNED_BC1 - Block compressed 1
• RES_VIEW_FORMAT_UNSIGNED_BC2 - Block compressed 2
• RES_VIEW_FORMAT_UNSIGNED_BC3 - Block compressed 3
• RES_VIEW_FORMAT_UNSIGNED_BC4 - Block compressed 4 unsigned
• RES_VIEW_FORMAT_SIGNED_BC4 - Block compressed 4 signed
• RES_VIEW_FORMAT_UNSIGNED_BC5 - Block compressed 5 unsigned
• RES_VIEW_FORMAT_SIGNED_BC5 - Block compressed 5 signed
• RES_VIEW_FORMAT_UNSIGNED_BC6H - Block compressed 6 unsigned half-float
• RES_VIEW_FORMAT_SIGNED_BC6H - Block compressed 6 signed half-float
• RES_VIEW_FORMAT_UNSIGNED_BC7 - Block compressed 7

See Also:

• Constant Field Values

CU_RES_VIEW_FORMAT_SINT_1X16

public static final int CU_RES_VIEW_FORMAT_SINT_1X16

Resource view format. (CUresourceViewFormat)

Enum values:

• RES_VIEW_FORMAT_NONE - No resource view format (use underlying resource format)
• RES_VIEW_FORMAT_UINT_1X8 - 1 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_UINT_2X8 - 2 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_UINT_4X8 - 4 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_SINT_1X8 - 1 channel signed 8-bit integers
• RES_VIEW_FORMAT_SINT_2X8 - 2 channel signed 8-bit integers
• RES_VIEW_FORMAT_SINT_4X8 - 4 channel signed 8-bit integers
• RES_VIEW_FORMAT_UINT_1X16 - 1 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_UINT_2X16 - 2 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_UINT_4X16 - 4 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_SINT_1X16 - 1 channel signed 16-bit integers
• RES_VIEW_FORMAT_SINT_2X16 - 2 channel signed 16-bit integers
• RES_VIEW_FORMAT_SINT_4X16 - 4 channel signed 16-bit integers
• RES_VIEW_FORMAT_UINT_1X32 - 1 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_UINT_2X32 - 2 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_UINT_4X32 - 4 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_SINT_1X32 - 1 channel signed 32-bit integers
• RES_VIEW_FORMAT_SINT_2X32 - 2 channel signed 32-bit integers
• RES_VIEW_FORMAT_SINT_4X32 - 4 channel signed 32-bit integers
• RES_VIEW_FORMAT_FLOAT_1X16 - 1 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_2X16 - 2 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_4X16 - 4 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_1X32 - 1 channel 32-bit floating point
• RES_VIEW_FORMAT_FLOAT_2X32 - 2 channel 32-bit floating point
• RES_VIEW_FORMAT_FLOAT_4X32 - 4 channel 32-bit floating point
• RES_VIEW_FORMAT_UNSIGNED_BC1 - Block compressed 1
• RES_VIEW_FORMAT_UNSIGNED_BC2 - Block compressed 2
• RES_VIEW_FORMAT_UNSIGNED_BC3 - Block compressed 3
• RES_VIEW_FORMAT_UNSIGNED_BC4 - Block compressed 4 unsigned
• RES_VIEW_FORMAT_SIGNED_BC4 - Block compressed 4 signed
• RES_VIEW_FORMAT_UNSIGNED_BC5 - Block compressed 5 unsigned
• RES_VIEW_FORMAT_SIGNED_BC5 - Block compressed 5 signed
• RES_VIEW_FORMAT_UNSIGNED_BC6H - Block compressed 6 unsigned half-float
• RES_VIEW_FORMAT_SIGNED_BC6H - Block compressed 6 signed half-float
• RES_VIEW_FORMAT_UNSIGNED_BC7 - Block compressed 7

See Also:

• Constant Field Values

CU_RES_VIEW_FORMAT_SINT_2X16

public static final int CU_RES_VIEW_FORMAT_SINT_2X16

Resource view format. (CUresourceViewFormat)

Enum values:

• RES_VIEW_FORMAT_NONE - No resource view format (use underlying resource format)
• RES_VIEW_FORMAT_UINT_1X8 - 1 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_UINT_2X8 - 2 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_UINT_4X8 - 4 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_SINT_1X8 - 1 channel signed 8-bit integers
• RES_VIEW_FORMAT_SINT_2X8 - 2 channel signed 8-bit integers
• RES_VIEW_FORMAT_SINT_4X8 - 4 channel signed 8-bit integers
• RES_VIEW_FORMAT_UINT_1X16 - 1 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_UINT_2X16 - 2 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_UINT_4X16 - 4 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_SINT_1X16 - 1 channel signed 16-bit integers
• RES_VIEW_FORMAT_SINT_2X16 - 2 channel signed 16-bit integers
• RES_VIEW_FORMAT_SINT_4X16 - 4 channel signed 16-bit integers
• RES_VIEW_FORMAT_UINT_1X32 - 1 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_UINT_2X32 - 2 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_UINT_4X32 - 4 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_SINT_1X32 - 1 channel signed 32-bit integers
• RES_VIEW_FORMAT_SINT_2X32 - 2 channel signed 32-bit integers
• RES_VIEW_FORMAT_SINT_4X32 - 4 channel signed 32-bit integers
• RES_VIEW_FORMAT_FLOAT_1X16 - 1 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_2X16 - 2 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_4X16 - 4 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_1X32 - 1 channel 32-bit floating point
• RES_VIEW_FORMAT_FLOAT_2X32 - 2 channel 32-bit floating point
• RES_VIEW_FORMAT_FLOAT_4X32 - 4 channel 32-bit floating point
• RES_VIEW_FORMAT_UNSIGNED_BC1 - Block compressed 1
• RES_VIEW_FORMAT_UNSIGNED_BC2 - Block compressed 2
• RES_VIEW_FORMAT_UNSIGNED_BC3 - Block compressed 3
• RES_VIEW_FORMAT_UNSIGNED_BC4 - Block compressed 4 unsigned
• RES_VIEW_FORMAT_SIGNED_BC4 - Block compressed 4 signed
• RES_VIEW_FORMAT_UNSIGNED_BC5 - Block compressed 5 unsigned
• RES_VIEW_FORMAT_SIGNED_BC5 - Block compressed 5 signed
• RES_VIEW_FORMAT_UNSIGNED_BC6H - Block compressed 6 unsigned half-float
• RES_VIEW_FORMAT_SIGNED_BC6H - Block compressed 6 signed half-float
• RES_VIEW_FORMAT_UNSIGNED_BC7 - Block compressed 7

See Also:

• Constant Field Values

CU_RES_VIEW_FORMAT_SINT_4X16

public static final int CU_RES_VIEW_FORMAT_SINT_4X16

Resource view format. (CUresourceViewFormat)

Enum values:

• RES_VIEW_FORMAT_NONE - No resource view format (use underlying resource format)
• RES_VIEW_FORMAT_UINT_1X8 - 1 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_UINT_2X8 - 2 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_UINT_4X8 - 4 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_SINT_1X8 - 1 channel signed 8-bit integers
• RES_VIEW_FORMAT_SINT_2X8 - 2 channel signed 8-bit integers
• RES_VIEW_FORMAT_SINT_4X8 - 4 channel signed 8-bit integers
• RES_VIEW_FORMAT_UINT_1X16 - 1 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_UINT_2X16 - 2 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_UINT_4X16 - 4 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_SINT_1X16 - 1 channel signed 16-bit integers
• RES_VIEW_FORMAT_SINT_2X16 - 2 channel signed 16-bit integers
• RES_VIEW_FORMAT_SINT_4X16 - 4 channel signed 16-bit integers
• RES_VIEW_FORMAT_UINT_1X32 - 1 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_UINT_2X32 - 2 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_UINT_4X32 - 4 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_SINT_1X32 - 1 channel signed 32-bit integers
• RES_VIEW_FORMAT_SINT_2X32 - 2 channel signed 32-bit integers
• RES_VIEW_FORMAT_SINT_4X32 - 4 channel signed 32-bit integers
• RES_VIEW_FORMAT_FLOAT_1X16 - 1 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_2X16 - 2 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_4X16 - 4 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_1X32 - 1 channel 32-bit floating point
• RES_VIEW_FORMAT_FLOAT_2X32 - 2 channel 32-bit floating point
• RES_VIEW_FORMAT_FLOAT_4X32 - 4 channel 32-bit floating point
• RES_VIEW_FORMAT_UNSIGNED_BC1 - Block compressed 1
• RES_VIEW_FORMAT_UNSIGNED_BC2 - Block compressed 2
• RES_VIEW_FORMAT_UNSIGNED_BC3 - Block compressed 3
• RES_VIEW_FORMAT_UNSIGNED_BC4 - Block compressed 4 unsigned
• RES_VIEW_FORMAT_SIGNED_BC4 - Block compressed 4 signed
• RES_VIEW_FORMAT_UNSIGNED_BC5 - Block compressed 5 unsigned
• RES_VIEW_FORMAT_SIGNED_BC5 - Block compressed 5 signed
• RES_VIEW_FORMAT_UNSIGNED_BC6H - Block compressed 6 unsigned half-float
• RES_VIEW_FORMAT_SIGNED_BC6H - Block compressed 6 signed half-float
• RES_VIEW_FORMAT_UNSIGNED_BC7 - Block compressed 7

See Also:

• Constant Field Values

CU_RES_VIEW_FORMAT_UINT_1X32

public static final int CU_RES_VIEW_FORMAT_UINT_1X32

Resource view format. (CUresourceViewFormat)

Enum values:

• RES_VIEW_FORMAT_NONE - No resource view format (use underlying resource format)
• RES_VIEW_FORMAT_UINT_1X8 - 1 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_UINT_2X8 - 2 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_UINT_4X8 - 4 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_SINT_1X8 - 1 channel signed 8-bit integers
• RES_VIEW_FORMAT_SINT_2X8 - 2 channel signed 8-bit integers
• RES_VIEW_FORMAT_SINT_4X8 - 4 channel signed 8-bit integers
• RES_VIEW_FORMAT_UINT_1X16 - 1 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_UINT_2X16 - 2 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_UINT_4X16 - 4 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_SINT_1X16 - 1 channel signed 16-bit integers
• RES_VIEW_FORMAT_SINT_2X16 - 2 channel signed 16-bit integers
• RES_VIEW_FORMAT_SINT_4X16 - 4 channel signed 16-bit integers
• RES_VIEW_FORMAT_UINT_1X32 - 1 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_UINT_2X32 - 2 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_UINT_4X32 - 4 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_SINT_1X32 - 1 channel signed 32-bit integers
• RES_VIEW_FORMAT_SINT_2X32 - 2 channel signed 32-bit integers
• RES_VIEW_FORMAT_SINT_4X32 - 4 channel signed 32-bit integers
• RES_VIEW_FORMAT_FLOAT_1X16 - 1 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_2X16 - 2 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_4X16 - 4 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_1X32 - 1 channel 32-bit floating point
• RES_VIEW_FORMAT_FLOAT_2X32 - 2 channel 32-bit floating point
• RES_VIEW_FORMAT_FLOAT_4X32 - 4 channel 32-bit floating point
• RES_VIEW_FORMAT_UNSIGNED_BC1 - Block compressed 1
• RES_VIEW_FORMAT_UNSIGNED_BC2 - Block compressed 2
• RES_VIEW_FORMAT_UNSIGNED_BC3 - Block compressed 3
• RES_VIEW_FORMAT_UNSIGNED_BC4 - Block compressed 4 unsigned
• RES_VIEW_FORMAT_SIGNED_BC4 - Block compressed 4 signed
• RES_VIEW_FORMAT_UNSIGNED_BC5 - Block compressed 5 unsigned
• RES_VIEW_FORMAT_SIGNED_BC5 - Block compressed 5 signed
• RES_VIEW_FORMAT_UNSIGNED_BC6H - Block compressed 6 unsigned half-float
• RES_VIEW_FORMAT_SIGNED_BC6H - Block compressed 6 signed half-float
• RES_VIEW_FORMAT_UNSIGNED_BC7 - Block compressed 7

See Also:

• Constant Field Values

CU_RES_VIEW_FORMAT_UINT_2X32

public static final int CU_RES_VIEW_FORMAT_UINT_2X32

Resource view format. (CUresourceViewFormat)

Enum values:

• RES_VIEW_FORMAT_NONE - No resource view format (use underlying resource format)
• RES_VIEW_FORMAT_UINT_1X8 - 1 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_UINT_2X8 - 2 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_UINT_4X8 - 4 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_SINT_1X8 - 1 channel signed 8-bit integers
• RES_VIEW_FORMAT_SINT_2X8 - 2 channel signed 8-bit integers
• RES_VIEW_FORMAT_SINT_4X8 - 4 channel signed 8-bit integers
• RES_VIEW_FORMAT_UINT_1X16 - 1 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_UINT_2X16 - 2 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_UINT_4X16 - 4 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_SINT_1X16 - 1 channel signed 16-bit integers
• RES_VIEW_FORMAT_SINT_2X16 - 2 channel signed 16-bit integers
• RES_VIEW_FORMAT_SINT_4X16 - 4 channel signed 16-bit integers
• RES_VIEW_FORMAT_UINT_1X32 - 1 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_UINT_2X32 - 2 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_UINT_4X32 - 4 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_SINT_1X32 - 1 channel signed 32-bit integers
• RES_VIEW_FORMAT_SINT_2X32 - 2 channel signed 32-bit integers
• RES_VIEW_FORMAT_SINT_4X32 - 4 channel signed 32-bit integers
• RES_VIEW_FORMAT_FLOAT_1X16 - 1 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_2X16 - 2 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_4X16 - 4 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_1X32 - 1 channel 32-bit floating point
• RES_VIEW_FORMAT_FLOAT_2X32 - 2 channel 32-bit floating point
• RES_VIEW_FORMAT_FLOAT_4X32 - 4 channel 32-bit floating point
• RES_VIEW_FORMAT_UNSIGNED_BC1 - Block compressed 1
• RES_VIEW_FORMAT_UNSIGNED_BC2 - Block compressed 2
• RES_VIEW_FORMAT_UNSIGNED_BC3 - Block compressed 3
• RES_VIEW_FORMAT_UNSIGNED_BC4 - Block compressed 4 unsigned
• RES_VIEW_FORMAT_SIGNED_BC4 - Block compressed 4 signed
• RES_VIEW_FORMAT_UNSIGNED_BC5 - Block compressed 5 unsigned
• RES_VIEW_FORMAT_SIGNED_BC5 - Block compressed 5 signed
• RES_VIEW_FORMAT_UNSIGNED_BC6H - Block compressed 6 unsigned half-float
• RES_VIEW_FORMAT_SIGNED_BC6H - Block compressed 6 signed half-float
• RES_VIEW_FORMAT_UNSIGNED_BC7 - Block compressed 7

See Also:

• Constant Field Values

CU_RES_VIEW_FORMAT_UINT_4X32

public static final int CU_RES_VIEW_FORMAT_UINT_4X32

Resource view format. (CUresourceViewFormat)

Enum values:

• RES_VIEW_FORMAT_NONE - No resource view format (use underlying resource format)
• RES_VIEW_FORMAT_UINT_1X8 - 1 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_UINT_2X8 - 2 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_UINT_4X8 - 4 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_SINT_1X8 - 1 channel signed 8-bit integers
• RES_VIEW_FORMAT_SINT_2X8 - 2 channel signed 8-bit integers
• RES_VIEW_FORMAT_SINT_4X8 - 4 channel signed 8-bit integers
• RES_VIEW_FORMAT_UINT_1X16 - 1 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_UINT_2X16 - 2 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_UINT_4X16 - 4 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_SINT_1X16 - 1 channel signed 16-bit integers
• RES_VIEW_FORMAT_SINT_2X16 - 2 channel signed 16-bit integers
• RES_VIEW_FORMAT_SINT_4X16 - 4 channel signed 16-bit integers
• RES_VIEW_FORMAT_UINT_1X32 - 1 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_UINT_2X32 - 2 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_UINT_4X32 - 4 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_SINT_1X32 - 1 channel signed 32-bit integers
• RES_VIEW_FORMAT_SINT_2X32 - 2 channel signed 32-bit integers
• RES_VIEW_FORMAT_SINT_4X32 - 4 channel signed 32-bit integers
• RES_VIEW_FORMAT_FLOAT_1X16 - 1 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_2X16 - 2 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_4X16 - 4 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_1X32 - 1 channel 32-bit floating point
• RES_VIEW_FORMAT_FLOAT_2X32 - 2 channel 32-bit floating point
• RES_VIEW_FORMAT_FLOAT_4X32 - 4 channel 32-bit floating point
• RES_VIEW_FORMAT_UNSIGNED_BC1 - Block compressed 1
• RES_VIEW_FORMAT_UNSIGNED_BC2 - Block compressed 2
• RES_VIEW_FORMAT_UNSIGNED_BC3 - Block compressed 3
• RES_VIEW_FORMAT_UNSIGNED_BC4 - Block compressed 4 unsigned
• RES_VIEW_FORMAT_SIGNED_BC4 - Block compressed 4 signed
• RES_VIEW_FORMAT_UNSIGNED_BC5 - Block compressed 5 unsigned
• RES_VIEW_FORMAT_SIGNED_BC5 - Block compressed 5 signed
• RES_VIEW_FORMAT_UNSIGNED_BC6H - Block compressed 6 unsigned half-float
• RES_VIEW_FORMAT_SIGNED_BC6H - Block compressed 6 signed half-float
• RES_VIEW_FORMAT_UNSIGNED_BC7 - Block compressed 7

See Also:

• Constant Field Values

CU_RES_VIEW_FORMAT_SINT_1X32

public static final int CU_RES_VIEW_FORMAT_SINT_1X32

Resource view format. (CUresourceViewFormat)

Enum values:

• RES_VIEW_FORMAT_NONE - No resource view format (use underlying resource format)
• RES_VIEW_FORMAT_UINT_1X8 - 1 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_UINT_2X8 - 2 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_UINT_4X8 - 4 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_SINT_1X8 - 1 channel signed 8-bit integers
• RES_VIEW_FORMAT_SINT_2X8 - 2 channel signed 8-bit integers
• RES_VIEW_FORMAT_SINT_4X8 - 4 channel signed 8-bit integers
• RES_VIEW_FORMAT_UINT_1X16 - 1 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_UINT_2X16 - 2 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_UINT_4X16 - 4 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_SINT_1X16 - 1 channel signed 16-bit integers
• RES_VIEW_FORMAT_SINT_2X16 - 2 channel signed 16-bit integers
• RES_VIEW_FORMAT_SINT_4X16 - 4 channel signed 16-bit integers
• RES_VIEW_FORMAT_UINT_1X32 - 1 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_UINT_2X32 - 2 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_UINT_4X32 - 4 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_SINT_1X32 - 1 channel signed 32-bit integers
• RES_VIEW_FORMAT_SINT_2X32 - 2 channel signed 32-bit integers
• RES_VIEW_FORMAT_SINT_4X32 - 4 channel signed 32-bit integers
• RES_VIEW_FORMAT_FLOAT_1X16 - 1 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_2X16 - 2 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_4X16 - 4 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_1X32 - 1 channel 32-bit floating point
• RES_VIEW_FORMAT_FLOAT_2X32 - 2 channel 32-bit floating point
• RES_VIEW_FORMAT_FLOAT_4X32 - 4 channel 32-bit floating point
• RES_VIEW_FORMAT_UNSIGNED_BC1 - Block compressed 1
• RES_VIEW_FORMAT_UNSIGNED_BC2 - Block compressed 2
• RES_VIEW_FORMAT_UNSIGNED_BC3 - Block compressed 3
• RES_VIEW_FORMAT_UNSIGNED_BC4 - Block compressed 4 unsigned
• RES_VIEW_FORMAT_SIGNED_BC4 - Block compressed 4 signed
• RES_VIEW_FORMAT_UNSIGNED_BC5 - Block compressed 5 unsigned
• RES_VIEW_FORMAT_SIGNED_BC5 - Block compressed 5 signed
• RES_VIEW_FORMAT_UNSIGNED_BC6H - Block compressed 6 unsigned half-float
• RES_VIEW_FORMAT_SIGNED_BC6H - Block compressed 6 signed half-float
• RES_VIEW_FORMAT_UNSIGNED_BC7 - Block compressed 7

See Also:

• Constant Field Values

CU_RES_VIEW_FORMAT_SINT_2X32

public static final int CU_RES_VIEW_FORMAT_SINT_2X32

Resource view format. (CUresourceViewFormat)

Enum values:

• RES_VIEW_FORMAT_NONE - No resource view format (use underlying resource format)
• RES_VIEW_FORMAT_UINT_1X8 - 1 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_UINT_2X8 - 2 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_UINT_4X8 - 4 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_SINT_1X8 - 1 channel signed 8-bit integers
• RES_VIEW_FORMAT_SINT_2X8 - 2 channel signed 8-bit integers
• RES_VIEW_FORMAT_SINT_4X8 - 4 channel signed 8-bit integers
• RES_VIEW_FORMAT_UINT_1X16 - 1 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_UINT_2X16 - 2 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_UINT_4X16 - 4 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_SINT_1X16 - 1 channel signed 16-bit integers
• RES_VIEW_FORMAT_SINT_2X16 - 2 channel signed 16-bit integers
• RES_VIEW_FORMAT_SINT_4X16 - 4 channel signed 16-bit integers
• RES_VIEW_FORMAT_UINT_1X32 - 1 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_UINT_2X32 - 2 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_UINT_4X32 - 4 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_SINT_1X32 - 1 channel signed 32-bit integers
• RES_VIEW_FORMAT_SINT_2X32 - 2 channel signed 32-bit integers
• RES_VIEW_FORMAT_SINT_4X32 - 4 channel signed 32-bit integers
• RES_VIEW_FORMAT_FLOAT_1X16 - 1 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_2X16 - 2 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_4X16 - 4 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_1X32 - 1 channel 32-bit floating point
• RES_VIEW_FORMAT_FLOAT_2X32 - 2 channel 32-bit floating point
• RES_VIEW_FORMAT_FLOAT_4X32 - 4 channel 32-bit floating point
• RES_VIEW_FORMAT_UNSIGNED_BC1 - Block compressed 1
• RES_VIEW_FORMAT_UNSIGNED_BC2 - Block compressed 2
• RES_VIEW_FORMAT_UNSIGNED_BC3 - Block compressed 3
• RES_VIEW_FORMAT_UNSIGNED_BC4 - Block compressed 4 unsigned
• RES_VIEW_FORMAT_SIGNED_BC4 - Block compressed 4 signed
• RES_VIEW_FORMAT_UNSIGNED_BC5 - Block compressed 5 unsigned
• RES_VIEW_FORMAT_SIGNED_BC5 - Block compressed 5 signed
• RES_VIEW_FORMAT_UNSIGNED_BC6H - Block compressed 6 unsigned half-float
• RES_VIEW_FORMAT_SIGNED_BC6H - Block compressed 6 signed half-float
• RES_VIEW_FORMAT_UNSIGNED_BC7 - Block compressed 7

See Also:

• Constant Field Values

CU_RES_VIEW_FORMAT_SINT_4X32

public static final int CU_RES_VIEW_FORMAT_SINT_4X32

Resource view format. (CUresourceViewFormat)

Enum values:

• RES_VIEW_FORMAT_NONE - No resource view format (use underlying resource format)
• RES_VIEW_FORMAT_UINT_1X8 - 1 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_UINT_2X8 - 2 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_UINT_4X8 - 4 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_SINT_1X8 - 1 channel signed 8-bit integers
• RES_VIEW_FORMAT_SINT_2X8 - 2 channel signed 8-bit integers
• RES_VIEW_FORMAT_SINT_4X8 - 4 channel signed 8-bit integers
• RES_VIEW_FORMAT_UINT_1X16 - 1 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_UINT_2X16 - 2 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_UINT_4X16 - 4 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_SINT_1X16 - 1 channel signed 16-bit integers
• RES_VIEW_FORMAT_SINT_2X16 - 2 channel signed 16-bit integers
• RES_VIEW_FORMAT_SINT_4X16 - 4 channel signed 16-bit integers
• RES_VIEW_FORMAT_UINT_1X32 - 1 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_UINT_2X32 - 2 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_UINT_4X32 - 4 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_SINT_1X32 - 1 channel signed 32-bit integers
• RES_VIEW_FORMAT_SINT_2X32 - 2 channel signed 32-bit integers
• RES_VIEW_FORMAT_SINT_4X32 - 4 channel signed 32-bit integers
• RES_VIEW_FORMAT_FLOAT_1X16 - 1 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_2X16 - 2 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_4X16 - 4 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_1X32 - 1 channel 32-bit floating point
• RES_VIEW_FORMAT_FLOAT_2X32 - 2 channel 32-bit floating point
• RES_VIEW_FORMAT_FLOAT_4X32 - 4 channel 32-bit floating point
• RES_VIEW_FORMAT_UNSIGNED_BC1 - Block compressed 1
• RES_VIEW_FORMAT_UNSIGNED_BC2 - Block compressed 2
• RES_VIEW_FORMAT_UNSIGNED_BC3 - Block compressed 3
• RES_VIEW_FORMAT_UNSIGNED_BC4 - Block compressed 4 unsigned
• RES_VIEW_FORMAT_SIGNED_BC4 - Block compressed 4 signed
• RES_VIEW_FORMAT_UNSIGNED_BC5 - Block compressed 5 unsigned
• RES_VIEW_FORMAT_SIGNED_BC5 - Block compressed 5 signed
• RES_VIEW_FORMAT_UNSIGNED_BC6H - Block compressed 6 unsigned half-float
• RES_VIEW_FORMAT_SIGNED_BC6H - Block compressed 6 signed half-float
• RES_VIEW_FORMAT_UNSIGNED_BC7 - Block compressed 7

See Also:

• Constant Field Values

CU_RES_VIEW_FORMAT_FLOAT_1X16

public static final int CU_RES_VIEW_FORMAT_FLOAT_1X16

Resource view format. (CUresourceViewFormat)

Enum values:

• RES_VIEW_FORMAT_NONE - No resource view format (use underlying resource format)
• RES_VIEW_FORMAT_UINT_1X8 - 1 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_UINT_2X8 - 2 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_UINT_4X8 - 4 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_SINT_1X8 - 1 channel signed 8-bit integers
• RES_VIEW_FORMAT_SINT_2X8 - 2 channel signed 8-bit integers
• RES_VIEW_FORMAT_SINT_4X8 - 4 channel signed 8-bit integers
• RES_VIEW_FORMAT_UINT_1X16 - 1 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_UINT_2X16 - 2 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_UINT_4X16 - 4 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_SINT_1X16 - 1 channel signed 16-bit integers
• RES_VIEW_FORMAT_SINT_2X16 - 2 channel signed 16-bit integers
• RES_VIEW_FORMAT_SINT_4X16 - 4 channel signed 16-bit integers
• RES_VIEW_FORMAT_UINT_1X32 - 1 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_UINT_2X32 - 2 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_UINT_4X32 - 4 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_SINT_1X32 - 1 channel signed 32-bit integers
• RES_VIEW_FORMAT_SINT_2X32 - 2 channel signed 32-bit integers
• RES_VIEW_FORMAT_SINT_4X32 - 4 channel signed 32-bit integers
• RES_VIEW_FORMAT_FLOAT_1X16 - 1 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_2X16 - 2 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_4X16 - 4 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_1X32 - 1 channel 32-bit floating point
• RES_VIEW_FORMAT_FLOAT_2X32 - 2 channel 32-bit floating point
• RES_VIEW_FORMAT_FLOAT_4X32 - 4 channel 32-bit floating point
• RES_VIEW_FORMAT_UNSIGNED_BC1 - Block compressed 1
• RES_VIEW_FORMAT_UNSIGNED_BC2 - Block compressed 2
• RES_VIEW_FORMAT_UNSIGNED_BC3 - Block compressed 3
• RES_VIEW_FORMAT_UNSIGNED_BC4 - Block compressed 4 unsigned
• RES_VIEW_FORMAT_SIGNED_BC4 - Block compressed 4 signed
• RES_VIEW_FORMAT_UNSIGNED_BC5 - Block compressed 5 unsigned
• RES_VIEW_FORMAT_SIGNED_BC5 - Block compressed 5 signed
• RES_VIEW_FORMAT_UNSIGNED_BC6H - Block compressed 6 unsigned half-float
• RES_VIEW_FORMAT_SIGNED_BC6H - Block compressed 6 signed half-float
• RES_VIEW_FORMAT_UNSIGNED_BC7 - Block compressed 7

See Also:

• Constant Field Values

CU_RES_VIEW_FORMAT_FLOAT_2X16

public static final int CU_RES_VIEW_FORMAT_FLOAT_2X16

Resource view format. (CUresourceViewFormat)

Enum values:

• RES_VIEW_FORMAT_NONE - No resource view format (use underlying resource format)
• RES_VIEW_FORMAT_UINT_1X8 - 1 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_UINT_2X8 - 2 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_UINT_4X8 - 4 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_SINT_1X8 - 1 channel signed 8-bit integers
• RES_VIEW_FORMAT_SINT_2X8 - 2 channel signed 8-bit integers
• RES_VIEW_FORMAT_SINT_4X8 - 4 channel signed 8-bit integers
• RES_VIEW_FORMAT_UINT_1X16 - 1 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_UINT_2X16 - 2 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_UINT_4X16 - 4 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_SINT_1X16 - 1 channel signed 16-bit integers
• RES_VIEW_FORMAT_SINT_2X16 - 2 channel signed 16-bit integers
• RES_VIEW_FORMAT_SINT_4X16 - 4 channel signed 16-bit integers
• RES_VIEW_FORMAT_UINT_1X32 - 1 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_UINT_2X32 - 2 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_UINT_4X32 - 4 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_SINT_1X32 - 1 channel signed 32-bit integers
• RES_VIEW_FORMAT_SINT_2X32 - 2 channel signed 32-bit integers
• RES_VIEW_FORMAT_SINT_4X32 - 4 channel signed 32-bit integers
• RES_VIEW_FORMAT_FLOAT_1X16 - 1 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_2X16 - 2 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_4X16 - 4 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_1X32 - 1 channel 32-bit floating point
• RES_VIEW_FORMAT_FLOAT_2X32 - 2 channel 32-bit floating point
• RES_VIEW_FORMAT_FLOAT_4X32 - 4 channel 32-bit floating point
• RES_VIEW_FORMAT_UNSIGNED_BC1 - Block compressed 1
• RES_VIEW_FORMAT_UNSIGNED_BC2 - Block compressed 2
• RES_VIEW_FORMAT_UNSIGNED_BC3 - Block compressed 3
• RES_VIEW_FORMAT_UNSIGNED_BC4 - Block compressed 4 unsigned
• RES_VIEW_FORMAT_SIGNED_BC4 - Block compressed 4 signed
• RES_VIEW_FORMAT_UNSIGNED_BC5 - Block compressed 5 unsigned
• RES_VIEW_FORMAT_SIGNED_BC5 - Block compressed 5 signed
• RES_VIEW_FORMAT_UNSIGNED_BC6H - Block compressed 6 unsigned half-float
• RES_VIEW_FORMAT_SIGNED_BC6H - Block compressed 6 signed half-float
• RES_VIEW_FORMAT_UNSIGNED_BC7 - Block compressed 7

See Also:

• Constant Field Values

CU_RES_VIEW_FORMAT_FLOAT_4X16

public static final int CU_RES_VIEW_FORMAT_FLOAT_4X16

Resource view format. (CUresourceViewFormat)

Enum values:

• RES_VIEW_FORMAT_NONE - No resource view format (use underlying resource format)
• RES_VIEW_FORMAT_UINT_1X8 - 1 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_UINT_2X8 - 2 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_UINT_4X8 - 4 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_SINT_1X8 - 1 channel signed 8-bit integers
• RES_VIEW_FORMAT_SINT_2X8 - 2 channel signed 8-bit integers
• RES_VIEW_FORMAT_SINT_4X8 - 4 channel signed 8-bit integers
• RES_VIEW_FORMAT_UINT_1X16 - 1 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_UINT_2X16 - 2 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_UINT_4X16 - 4 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_SINT_1X16 - 1 channel signed 16-bit integers
• RES_VIEW_FORMAT_SINT_2X16 - 2 channel signed 16-bit integers
• RES_VIEW_FORMAT_SINT_4X16 - 4 channel signed 16-bit integers
• RES_VIEW_FORMAT_UINT_1X32 - 1 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_UINT_2X32 - 2 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_UINT_4X32 - 4 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_SINT_1X32 - 1 channel signed 32-bit integers
• RES_VIEW_FORMAT_SINT_2X32 - 2 channel signed 32-bit integers
• RES_VIEW_FORMAT_SINT_4X32 - 4 channel signed 32-bit integers
• RES_VIEW_FORMAT_FLOAT_1X16 - 1 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_2X16 - 2 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_4X16 - 4 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_1X32 - 1 channel 32-bit floating point
• RES_VIEW_FORMAT_FLOAT_2X32 - 2 channel 32-bit floating point
• RES_VIEW_FORMAT_FLOAT_4X32 - 4 channel 32-bit floating point
• RES_VIEW_FORMAT_UNSIGNED_BC1 - Block compressed 1
• RES_VIEW_FORMAT_UNSIGNED_BC2 - Block compressed 2
• RES_VIEW_FORMAT_UNSIGNED_BC3 - Block compressed 3
• RES_VIEW_FORMAT_UNSIGNED_BC4 - Block compressed 4 unsigned
• RES_VIEW_FORMAT_SIGNED_BC4 - Block compressed 4 signed
• RES_VIEW_FORMAT_UNSIGNED_BC5 - Block compressed 5 unsigned
• RES_VIEW_FORMAT_SIGNED_BC5 - Block compressed 5 signed
• RES_VIEW_FORMAT_UNSIGNED_BC6H - Block compressed 6 unsigned half-float
• RES_VIEW_FORMAT_SIGNED_BC6H - Block compressed 6 signed half-float
• RES_VIEW_FORMAT_UNSIGNED_BC7 - Block compressed 7

See Also:

• Constant Field Values

CU_RES_VIEW_FORMAT_FLOAT_1X32

public static final int CU_RES_VIEW_FORMAT_FLOAT_1X32

Resource view format. (CUresourceViewFormat)

Enum values:

• RES_VIEW_FORMAT_NONE - No resource view format (use underlying resource format)
• RES_VIEW_FORMAT_UINT_1X8 - 1 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_UINT_2X8 - 2 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_UINT_4X8 - 4 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_SINT_1X8 - 1 channel signed 8-bit integers
• RES_VIEW_FORMAT_SINT_2X8 - 2 channel signed 8-bit integers
• RES_VIEW_FORMAT_SINT_4X8 - 4 channel signed 8-bit integers
• RES_VIEW_FORMAT_UINT_1X16 - 1 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_UINT_2X16 - 2 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_UINT_4X16 - 4 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_SINT_1X16 - 1 channel signed 16-bit integers
• RES_VIEW_FORMAT_SINT_2X16 - 2 channel signed 16-bit integers
• RES_VIEW_FORMAT_SINT_4X16 - 4 channel signed 16-bit integers
• RES_VIEW_FORMAT_UINT_1X32 - 1 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_UINT_2X32 - 2 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_UINT_4X32 - 4 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_SINT_1X32 - 1 channel signed 32-bit integers
• RES_VIEW_FORMAT_SINT_2X32 - 2 channel signed 32-bit integers
• RES_VIEW_FORMAT_SINT_4X32 - 4 channel signed 32-bit integers
• RES_VIEW_FORMAT_FLOAT_1X16 - 1 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_2X16 - 2 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_4X16 - 4 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_1X32 - 1 channel 32-bit floating point
• RES_VIEW_FORMAT_FLOAT_2X32 - 2 channel 32-bit floating point
• RES_VIEW_FORMAT_FLOAT_4X32 - 4 channel 32-bit floating point
• RES_VIEW_FORMAT_UNSIGNED_BC1 - Block compressed 1
• RES_VIEW_FORMAT_UNSIGNED_BC2 - Block compressed 2
• RES_VIEW_FORMAT_UNSIGNED_BC3 - Block compressed 3
• RES_VIEW_FORMAT_UNSIGNED_BC4 - Block compressed 4 unsigned
• RES_VIEW_FORMAT_SIGNED_BC4 - Block compressed 4 signed
• RES_VIEW_FORMAT_UNSIGNED_BC5 - Block compressed 5 unsigned
• RES_VIEW_FORMAT_SIGNED_BC5 - Block compressed 5 signed
• RES_VIEW_FORMAT_UNSIGNED_BC6H - Block compressed 6 unsigned half-float
• RES_VIEW_FORMAT_SIGNED_BC6H - Block compressed 6 signed half-float
• RES_VIEW_FORMAT_UNSIGNED_BC7 - Block compressed 7

See Also:

• Constant Field Values

CU_RES_VIEW_FORMAT_FLOAT_2X32

public static final int CU_RES_VIEW_FORMAT_FLOAT_2X32

Resource view format. (CUresourceViewFormat)

Enum values:

• RES_VIEW_FORMAT_NONE - No resource view format (use underlying resource format)
• RES_VIEW_FORMAT_UINT_1X8 - 1 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_UINT_2X8 - 2 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_UINT_4X8 - 4 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_SINT_1X8 - 1 channel signed 8-bit integers
• RES_VIEW_FORMAT_SINT_2X8 - 2 channel signed 8-bit integers
• RES_VIEW_FORMAT_SINT_4X8 - 4 channel signed 8-bit integers
• RES_VIEW_FORMAT_UINT_1X16 - 1 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_UINT_2X16 - 2 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_UINT_4X16 - 4 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_SINT_1X16 - 1 channel signed 16-bit integers
• RES_VIEW_FORMAT_SINT_2X16 - 2 channel signed 16-bit integers
• RES_VIEW_FORMAT_SINT_4X16 - 4 channel signed 16-bit integers
• RES_VIEW_FORMAT_UINT_1X32 - 1 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_UINT_2X32 - 2 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_UINT_4X32 - 4 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_SINT_1X32 - 1 channel signed 32-bit integers
• RES_VIEW_FORMAT_SINT_2X32 - 2 channel signed 32-bit integers
• RES_VIEW_FORMAT_SINT_4X32 - 4 channel signed 32-bit integers
• RES_VIEW_FORMAT_FLOAT_1X16 - 1 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_2X16 - 2 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_4X16 - 4 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_1X32 - 1 channel 32-bit floating point
• RES_VIEW_FORMAT_FLOAT_2X32 - 2 channel 32-bit floating point
• RES_VIEW_FORMAT_FLOAT_4X32 - 4 channel 32-bit floating point
• RES_VIEW_FORMAT_UNSIGNED_BC1 - Block compressed 1
• RES_VIEW_FORMAT_UNSIGNED_BC2 - Block compressed 2
• RES_VIEW_FORMAT_UNSIGNED_BC3 - Block compressed 3
• RES_VIEW_FORMAT_UNSIGNED_BC4 - Block compressed 4 unsigned
• RES_VIEW_FORMAT_SIGNED_BC4 - Block compressed 4 signed
• RES_VIEW_FORMAT_UNSIGNED_BC5 - Block compressed 5 unsigned
• RES_VIEW_FORMAT_SIGNED_BC5 - Block compressed 5 signed
• RES_VIEW_FORMAT_UNSIGNED_BC6H - Block compressed 6 unsigned half-float
• RES_VIEW_FORMAT_SIGNED_BC6H - Block compressed 6 signed half-float
• RES_VIEW_FORMAT_UNSIGNED_BC7 - Block compressed 7

See Also:

• Constant Field Values

CU_RES_VIEW_FORMAT_FLOAT_4X32

public static final int CU_RES_VIEW_FORMAT_FLOAT_4X32

Resource view format. (CUresourceViewFormat)

Enum values:

• RES_VIEW_FORMAT_NONE - No resource view format (use underlying resource format)
• RES_VIEW_FORMAT_UINT_1X8 - 1 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_UINT_2X8 - 2 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_UINT_4X8 - 4 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_SINT_1X8 - 1 channel signed 8-bit integers
• RES_VIEW_FORMAT_SINT_2X8 - 2 channel signed 8-bit integers
• RES_VIEW_FORMAT_SINT_4X8 - 4 channel signed 8-bit integers
• RES_VIEW_FORMAT_UINT_1X16 - 1 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_UINT_2X16 - 2 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_UINT_4X16 - 4 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_SINT_1X16 - 1 channel signed 16-bit integers
• RES_VIEW_FORMAT_SINT_2X16 - 2 channel signed 16-bit integers
• RES_VIEW_FORMAT_SINT_4X16 - 4 channel signed 16-bit integers
• RES_VIEW_FORMAT_UINT_1X32 - 1 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_UINT_2X32 - 2 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_UINT_4X32 - 4 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_SINT_1X32 - 1 channel signed 32-bit integers
• RES_VIEW_FORMAT_SINT_2X32 - 2 channel signed 32-bit integers
• RES_VIEW_FORMAT_SINT_4X32 - 4 channel signed 32-bit integers
• RES_VIEW_FORMAT_FLOAT_1X16 - 1 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_2X16 - 2 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_4X16 - 4 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_1X32 - 1 channel 32-bit floating point
• RES_VIEW_FORMAT_FLOAT_2X32 - 2 channel 32-bit floating point
• RES_VIEW_FORMAT_FLOAT_4X32 - 4 channel 32-bit floating point
• RES_VIEW_FORMAT_UNSIGNED_BC1 - Block compressed 1
• RES_VIEW_FORMAT_UNSIGNED_BC2 - Block compressed 2
• RES_VIEW_FORMAT_UNSIGNED_BC3 - Block compressed 3
• RES_VIEW_FORMAT_UNSIGNED_BC4 - Block compressed 4 unsigned
• RES_VIEW_FORMAT_SIGNED_BC4 - Block compressed 4 signed
• RES_VIEW_FORMAT_UNSIGNED_BC5 - Block compressed 5 unsigned
• RES_VIEW_FORMAT_SIGNED_BC5 - Block compressed 5 signed
• RES_VIEW_FORMAT_UNSIGNED_BC6H - Block compressed 6 unsigned half-float
• RES_VIEW_FORMAT_SIGNED_BC6H - Block compressed 6 signed half-float
• RES_VIEW_FORMAT_UNSIGNED_BC7 - Block compressed 7

See Also:

• Constant Field Values

CU_RES_VIEW_FORMAT_UNSIGNED_BC1

public static final int CU_RES_VIEW_FORMAT_UNSIGNED_BC1

Resource view format. (CUresourceViewFormat)

Enum values:

• RES_VIEW_FORMAT_NONE - No resource view format (use underlying resource format)
• RES_VIEW_FORMAT_UINT_1X8 - 1 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_UINT_2X8 - 2 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_UINT_4X8 - 4 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_SINT_1X8 - 1 channel signed 8-bit integers
• RES_VIEW_FORMAT_SINT_2X8 - 2 channel signed 8-bit integers
• RES_VIEW_FORMAT_SINT_4X8 - 4 channel signed 8-bit integers
• RES_VIEW_FORMAT_UINT_1X16 - 1 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_UINT_2X16 - 2 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_UINT_4X16 - 4 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_SINT_1X16 - 1 channel signed 16-bit integers
• RES_VIEW_FORMAT_SINT_2X16 - 2 channel signed 16-bit integers
• RES_VIEW_FORMAT_SINT_4X16 - 4 channel signed 16-bit integers
• RES_VIEW_FORMAT_UINT_1X32 - 1 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_UINT_2X32 - 2 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_UINT_4X32 - 4 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_SINT_1X32 - 1 channel signed 32-bit integers
• RES_VIEW_FORMAT_SINT_2X32 - 2 channel signed 32-bit integers
• RES_VIEW_FORMAT_SINT_4X32 - 4 channel signed 32-bit integers
• RES_VIEW_FORMAT_FLOAT_1X16 - 1 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_2X16 - 2 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_4X16 - 4 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_1X32 - 1 channel 32-bit floating point
• RES_VIEW_FORMAT_FLOAT_2X32 - 2 channel 32-bit floating point
• RES_VIEW_FORMAT_FLOAT_4X32 - 4 channel 32-bit floating point
• RES_VIEW_FORMAT_UNSIGNED_BC1 - Block compressed 1
• RES_VIEW_FORMAT_UNSIGNED_BC2 - Block compressed 2
• RES_VIEW_FORMAT_UNSIGNED_BC3 - Block compressed 3
• RES_VIEW_FORMAT_UNSIGNED_BC4 - Block compressed 4 unsigned
• RES_VIEW_FORMAT_SIGNED_BC4 - Block compressed 4 signed
• RES_VIEW_FORMAT_UNSIGNED_BC5 - Block compressed 5 unsigned
• RES_VIEW_FORMAT_SIGNED_BC5 - Block compressed 5 signed
• RES_VIEW_FORMAT_UNSIGNED_BC6H - Block compressed 6 unsigned half-float
• RES_VIEW_FORMAT_SIGNED_BC6H - Block compressed 6 signed half-float
• RES_VIEW_FORMAT_UNSIGNED_BC7 - Block compressed 7

See Also:

• Constant Field Values

CU_RES_VIEW_FORMAT_UNSIGNED_BC2

public static final int CU_RES_VIEW_FORMAT_UNSIGNED_BC2

Resource view format. (CUresourceViewFormat)

Enum values:

• RES_VIEW_FORMAT_NONE - No resource view format (use underlying resource format)
• RES_VIEW_FORMAT_UINT_1X8 - 1 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_UINT_2X8 - 2 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_UINT_4X8 - 4 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_SINT_1X8 - 1 channel signed 8-bit integers
• RES_VIEW_FORMAT_SINT_2X8 - 2 channel signed 8-bit integers
• RES_VIEW_FORMAT_SINT_4X8 - 4 channel signed 8-bit integers
• RES_VIEW_FORMAT_UINT_1X16 - 1 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_UINT_2X16 - 2 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_UINT_4X16 - 4 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_SINT_1X16 - 1 channel signed 16-bit integers
• RES_VIEW_FORMAT_SINT_2X16 - 2 channel signed 16-bit integers
• RES_VIEW_FORMAT_SINT_4X16 - 4 channel signed 16-bit integers
• RES_VIEW_FORMAT_UINT_1X32 - 1 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_UINT_2X32 - 2 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_UINT_4X32 - 4 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_SINT_1X32 - 1 channel signed 32-bit integers
• RES_VIEW_FORMAT_SINT_2X32 - 2 channel signed 32-bit integers
• RES_VIEW_FORMAT_SINT_4X32 - 4 channel signed 32-bit integers
• RES_VIEW_FORMAT_FLOAT_1X16 - 1 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_2X16 - 2 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_4X16 - 4 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_1X32 - 1 channel 32-bit floating point
• RES_VIEW_FORMAT_FLOAT_2X32 - 2 channel 32-bit floating point
• RES_VIEW_FORMAT_FLOAT_4X32 - 4 channel 32-bit floating point
• RES_VIEW_FORMAT_UNSIGNED_BC1 - Block compressed 1
• RES_VIEW_FORMAT_UNSIGNED_BC2 - Block compressed 2
• RES_VIEW_FORMAT_UNSIGNED_BC3 - Block compressed 3
• RES_VIEW_FORMAT_UNSIGNED_BC4 - Block compressed 4 unsigned
• RES_VIEW_FORMAT_SIGNED_BC4 - Block compressed 4 signed
• RES_VIEW_FORMAT_UNSIGNED_BC5 - Block compressed 5 unsigned
• RES_VIEW_FORMAT_SIGNED_BC5 - Block compressed 5 signed
• RES_VIEW_FORMAT_UNSIGNED_BC6H - Block compressed 6 unsigned half-float
• RES_VIEW_FORMAT_SIGNED_BC6H - Block compressed 6 signed half-float
• RES_VIEW_FORMAT_UNSIGNED_BC7 - Block compressed 7

See Also:

• Constant Field Values

CU_RES_VIEW_FORMAT_UNSIGNED_BC3

public static final int CU_RES_VIEW_FORMAT_UNSIGNED_BC3

Resource view format. (CUresourceViewFormat)

Enum values:

• RES_VIEW_FORMAT_NONE - No resource view format (use underlying resource format)
• RES_VIEW_FORMAT_UINT_1X8 - 1 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_UINT_2X8 - 2 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_UINT_4X8 - 4 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_SINT_1X8 - 1 channel signed 8-bit integers
• RES_VIEW_FORMAT_SINT_2X8 - 2 channel signed 8-bit integers
• RES_VIEW_FORMAT_SINT_4X8 - 4 channel signed 8-bit integers
• RES_VIEW_FORMAT_UINT_1X16 - 1 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_UINT_2X16 - 2 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_UINT_4X16 - 4 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_SINT_1X16 - 1 channel signed 16-bit integers
• RES_VIEW_FORMAT_SINT_2X16 - 2 channel signed 16-bit integers
• RES_VIEW_FORMAT_SINT_4X16 - 4 channel signed 16-bit integers
• RES_VIEW_FORMAT_UINT_1X32 - 1 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_UINT_2X32 - 2 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_UINT_4X32 - 4 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_SINT_1X32 - 1 channel signed 32-bit integers
• RES_VIEW_FORMAT_SINT_2X32 - 2 channel signed 32-bit integers
• RES_VIEW_FORMAT_SINT_4X32 - 4 channel signed 32-bit integers
• RES_VIEW_FORMAT_FLOAT_1X16 - 1 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_2X16 - 2 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_4X16 - 4 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_1X32 - 1 channel 32-bit floating point
• RES_VIEW_FORMAT_FLOAT_2X32 - 2 channel 32-bit floating point
• RES_VIEW_FORMAT_FLOAT_4X32 - 4 channel 32-bit floating point
• RES_VIEW_FORMAT_UNSIGNED_BC1 - Block compressed 1
• RES_VIEW_FORMAT_UNSIGNED_BC2 - Block compressed 2
• RES_VIEW_FORMAT_UNSIGNED_BC3 - Block compressed 3
• RES_VIEW_FORMAT_UNSIGNED_BC4 - Block compressed 4 unsigned
• RES_VIEW_FORMAT_SIGNED_BC4 - Block compressed 4 signed
• RES_VIEW_FORMAT_UNSIGNED_BC5 - Block compressed 5 unsigned
• RES_VIEW_FORMAT_SIGNED_BC5 - Block compressed 5 signed
• RES_VIEW_FORMAT_UNSIGNED_BC6H - Block compressed 6 unsigned half-float
• RES_VIEW_FORMAT_SIGNED_BC6H - Block compressed 6 signed half-float
• RES_VIEW_FORMAT_UNSIGNED_BC7 - Block compressed 7

See Also:

• Constant Field Values

CU_RES_VIEW_FORMAT_UNSIGNED_BC4

public static final int CU_RES_VIEW_FORMAT_UNSIGNED_BC4

Resource view format. (CUresourceViewFormat)

Enum values:

• RES_VIEW_FORMAT_NONE - No resource view format (use underlying resource format)
• RES_VIEW_FORMAT_UINT_1X8 - 1 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_UINT_2X8 - 2 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_UINT_4X8 - 4 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_SINT_1X8 - 1 channel signed 8-bit integers
• RES_VIEW_FORMAT_SINT_2X8 - 2 channel signed 8-bit integers
• RES_VIEW_FORMAT_SINT_4X8 - 4 channel signed 8-bit integers
• RES_VIEW_FORMAT_UINT_1X16 - 1 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_UINT_2X16 - 2 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_UINT_4X16 - 4 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_SINT_1X16 - 1 channel signed 16-bit integers
• RES_VIEW_FORMAT_SINT_2X16 - 2 channel signed 16-bit integers
• RES_VIEW_FORMAT_SINT_4X16 - 4 channel signed 16-bit integers
• RES_VIEW_FORMAT_UINT_1X32 - 1 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_UINT_2X32 - 2 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_UINT_4X32 - 4 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_SINT_1X32 - 1 channel signed 32-bit integers
• RES_VIEW_FORMAT_SINT_2X32 - 2 channel signed 32-bit integers
• RES_VIEW_FORMAT_SINT_4X32 - 4 channel signed 32-bit integers
• RES_VIEW_FORMAT_FLOAT_1X16 - 1 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_2X16 - 2 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_4X16 - 4 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_1X32 - 1 channel 32-bit floating point
• RES_VIEW_FORMAT_FLOAT_2X32 - 2 channel 32-bit floating point
• RES_VIEW_FORMAT_FLOAT_4X32 - 4 channel 32-bit floating point
• RES_VIEW_FORMAT_UNSIGNED_BC1 - Block compressed 1
• RES_VIEW_FORMAT_UNSIGNED_BC2 - Block compressed 2
• RES_VIEW_FORMAT_UNSIGNED_BC3 - Block compressed 3
• RES_VIEW_FORMAT_UNSIGNED_BC4 - Block compressed 4 unsigned
• RES_VIEW_FORMAT_SIGNED_BC4 - Block compressed 4 signed
• RES_VIEW_FORMAT_UNSIGNED_BC5 - Block compressed 5 unsigned
• RES_VIEW_FORMAT_SIGNED_BC5 - Block compressed 5 signed
• RES_VIEW_FORMAT_UNSIGNED_BC6H - Block compressed 6 unsigned half-float
• RES_VIEW_FORMAT_SIGNED_BC6H - Block compressed 6 signed half-float
• RES_VIEW_FORMAT_UNSIGNED_BC7 - Block compressed 7

See Also:

• Constant Field Values

CU_RES_VIEW_FORMAT_SIGNED_BC4

public static final int CU_RES_VIEW_FORMAT_SIGNED_BC4

Resource view format. (CUresourceViewFormat)

Enum values:

• RES_VIEW_FORMAT_NONE - No resource view format (use underlying resource format)
• RES_VIEW_FORMAT_UINT_1X8 - 1 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_UINT_2X8 - 2 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_UINT_4X8 - 4 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_SINT_1X8 - 1 channel signed 8-bit integers
• RES_VIEW_FORMAT_SINT_2X8 - 2 channel signed 8-bit integers
• RES_VIEW_FORMAT_SINT_4X8 - 4 channel signed 8-bit integers
• RES_VIEW_FORMAT_UINT_1X16 - 1 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_UINT_2X16 - 2 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_UINT_4X16 - 4 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_SINT_1X16 - 1 channel signed 16-bit integers
• RES_VIEW_FORMAT_SINT_2X16 - 2 channel signed 16-bit integers
• RES_VIEW_FORMAT_SINT_4X16 - 4 channel signed 16-bit integers
• RES_VIEW_FORMAT_UINT_1X32 - 1 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_UINT_2X32 - 2 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_UINT_4X32 - 4 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_SINT_1X32 - 1 channel signed 32-bit integers
• RES_VIEW_FORMAT_SINT_2X32 - 2 channel signed 32-bit integers
• RES_VIEW_FORMAT_SINT_4X32 - 4 channel signed 32-bit integers
• RES_VIEW_FORMAT_FLOAT_1X16 - 1 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_2X16 - 2 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_4X16 - 4 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_1X32 - 1 channel 32-bit floating point
• RES_VIEW_FORMAT_FLOAT_2X32 - 2 channel 32-bit floating point
• RES_VIEW_FORMAT_FLOAT_4X32 - 4 channel 32-bit floating point
• RES_VIEW_FORMAT_UNSIGNED_BC1 - Block compressed 1
• RES_VIEW_FORMAT_UNSIGNED_BC2 - Block compressed 2
• RES_VIEW_FORMAT_UNSIGNED_BC3 - Block compressed 3
• RES_VIEW_FORMAT_UNSIGNED_BC4 - Block compressed 4 unsigned
• RES_VIEW_FORMAT_SIGNED_BC4 - Block compressed 4 signed
• RES_VIEW_FORMAT_UNSIGNED_BC5 - Block compressed 5 unsigned
• RES_VIEW_FORMAT_SIGNED_BC5 - Block compressed 5 signed
• RES_VIEW_FORMAT_UNSIGNED_BC6H - Block compressed 6 unsigned half-float
• RES_VIEW_FORMAT_SIGNED_BC6H - Block compressed 6 signed half-float
• RES_VIEW_FORMAT_UNSIGNED_BC7 - Block compressed 7

See Also:

• Constant Field Values

CU_RES_VIEW_FORMAT_UNSIGNED_BC5

public static final int CU_RES_VIEW_FORMAT_UNSIGNED_BC5

Resource view format. (CUresourceViewFormat)

Enum values:

• RES_VIEW_FORMAT_NONE - No resource view format (use underlying resource format)
• RES_VIEW_FORMAT_UINT_1X8 - 1 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_UINT_2X8 - 2 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_UINT_4X8 - 4 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_SINT_1X8 - 1 channel signed 8-bit integers
• RES_VIEW_FORMAT_SINT_2X8 - 2 channel signed 8-bit integers
• RES_VIEW_FORMAT_SINT_4X8 - 4 channel signed 8-bit integers
• RES_VIEW_FORMAT_UINT_1X16 - 1 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_UINT_2X16 - 2 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_UINT_4X16 - 4 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_SINT_1X16 - 1 channel signed 16-bit integers
• RES_VIEW_FORMAT_SINT_2X16 - 2 channel signed 16-bit integers
• RES_VIEW_FORMAT_SINT_4X16 - 4 channel signed 16-bit integers
• RES_VIEW_FORMAT_UINT_1X32 - 1 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_UINT_2X32 - 2 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_UINT_4X32 - 4 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_SINT_1X32 - 1 channel signed 32-bit integers
• RES_VIEW_FORMAT_SINT_2X32 - 2 channel signed 32-bit integers
• RES_VIEW_FORMAT_SINT_4X32 - 4 channel signed 32-bit integers
• RES_VIEW_FORMAT_FLOAT_1X16 - 1 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_2X16 - 2 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_4X16 - 4 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_1X32 - 1 channel 32-bit floating point
• RES_VIEW_FORMAT_FLOAT_2X32 - 2 channel 32-bit floating point
• RES_VIEW_FORMAT_FLOAT_4X32 - 4 channel 32-bit floating point
• RES_VIEW_FORMAT_UNSIGNED_BC1 - Block compressed 1
• RES_VIEW_FORMAT_UNSIGNED_BC2 - Block compressed 2
• RES_VIEW_FORMAT_UNSIGNED_BC3 - Block compressed 3
• RES_VIEW_FORMAT_UNSIGNED_BC4 - Block compressed 4 unsigned
• RES_VIEW_FORMAT_SIGNED_BC4 - Block compressed 4 signed
• RES_VIEW_FORMAT_UNSIGNED_BC5 - Block compressed 5 unsigned
• RES_VIEW_FORMAT_SIGNED_BC5 - Block compressed 5 signed
• RES_VIEW_FORMAT_UNSIGNED_BC6H - Block compressed 6 unsigned half-float
• RES_VIEW_FORMAT_SIGNED_BC6H - Block compressed 6 signed half-float
• RES_VIEW_FORMAT_UNSIGNED_BC7 - Block compressed 7

See Also:

• Constant Field Values

CU_RES_VIEW_FORMAT_SIGNED_BC5

public static final int CU_RES_VIEW_FORMAT_SIGNED_BC5

Resource view format. (CUresourceViewFormat)

Enum values:

• RES_VIEW_FORMAT_NONE - No resource view format (use underlying resource format)
• RES_VIEW_FORMAT_UINT_1X8 - 1 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_UINT_2X8 - 2 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_UINT_4X8 - 4 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_SINT_1X8 - 1 channel signed 8-bit integers
• RES_VIEW_FORMAT_SINT_2X8 - 2 channel signed 8-bit integers
• RES_VIEW_FORMAT_SINT_4X8 - 4 channel signed 8-bit integers
• RES_VIEW_FORMAT_UINT_1X16 - 1 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_UINT_2X16 - 2 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_UINT_4X16 - 4 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_SINT_1X16 - 1 channel signed 16-bit integers
• RES_VIEW_FORMAT_SINT_2X16 - 2 channel signed 16-bit integers
• RES_VIEW_FORMAT_SINT_4X16 - 4 channel signed 16-bit integers
• RES_VIEW_FORMAT_UINT_1X32 - 1 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_UINT_2X32 - 2 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_UINT_4X32 - 4 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_SINT_1X32 - 1 channel signed 32-bit integers
• RES_VIEW_FORMAT_SINT_2X32 - 2 channel signed 32-bit integers
• RES_VIEW_FORMAT_SINT_4X32 - 4 channel signed 32-bit integers
• RES_VIEW_FORMAT_FLOAT_1X16 - 1 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_2X16 - 2 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_4X16 - 4 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_1X32 - 1 channel 32-bit floating point
• RES_VIEW_FORMAT_FLOAT_2X32 - 2 channel 32-bit floating point
• RES_VIEW_FORMAT_FLOAT_4X32 - 4 channel 32-bit floating point
• RES_VIEW_FORMAT_UNSIGNED_BC1 - Block compressed 1
• RES_VIEW_FORMAT_UNSIGNED_BC2 - Block compressed 2
• RES_VIEW_FORMAT_UNSIGNED_BC3 - Block compressed 3
• RES_VIEW_FORMAT_UNSIGNED_BC4 - Block compressed 4 unsigned
• RES_VIEW_FORMAT_SIGNED_BC4 - Block compressed 4 signed
• RES_VIEW_FORMAT_UNSIGNED_BC5 - Block compressed 5 unsigned
• RES_VIEW_FORMAT_SIGNED_BC5 - Block compressed 5 signed
• RES_VIEW_FORMAT_UNSIGNED_BC6H - Block compressed 6 unsigned half-float
• RES_VIEW_FORMAT_SIGNED_BC6H - Block compressed 6 signed half-float
• RES_VIEW_FORMAT_UNSIGNED_BC7 - Block compressed 7

See Also:

• Constant Field Values

CU_RES_VIEW_FORMAT_UNSIGNED_BC6H

public static final int CU_RES_VIEW_FORMAT_UNSIGNED_BC6H

Resource view format. (CUresourceViewFormat)

Enum values:

• RES_VIEW_FORMAT_NONE - No resource view format (use underlying resource format)
• RES_VIEW_FORMAT_UINT_1X8 - 1 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_UINT_2X8 - 2 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_UINT_4X8 - 4 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_SINT_1X8 - 1 channel signed 8-bit integers
• RES_VIEW_FORMAT_SINT_2X8 - 2 channel signed 8-bit integers
• RES_VIEW_FORMAT_SINT_4X8 - 4 channel signed 8-bit integers
• RES_VIEW_FORMAT_UINT_1X16 - 1 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_UINT_2X16 - 2 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_UINT_4X16 - 4 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_SINT_1X16 - 1 channel signed 16-bit integers
• RES_VIEW_FORMAT_SINT_2X16 - 2 channel signed 16-bit integers
• RES_VIEW_FORMAT_SINT_4X16 - 4 channel signed 16-bit integers
• RES_VIEW_FORMAT_UINT_1X32 - 1 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_UINT_2X32 - 2 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_UINT_4X32 - 4 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_SINT_1X32 - 1 channel signed 32-bit integers
• RES_VIEW_FORMAT_SINT_2X32 - 2 channel signed 32-bit integers
• RES_VIEW_FORMAT_SINT_4X32 - 4 channel signed 32-bit integers
• RES_VIEW_FORMAT_FLOAT_1X16 - 1 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_2X16 - 2 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_4X16 - 4 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_1X32 - 1 channel 32-bit floating point
• RES_VIEW_FORMAT_FLOAT_2X32 - 2 channel 32-bit floating point
• RES_VIEW_FORMAT_FLOAT_4X32 - 4 channel 32-bit floating point
• RES_VIEW_FORMAT_UNSIGNED_BC1 - Block compressed 1
• RES_VIEW_FORMAT_UNSIGNED_BC2 - Block compressed 2
• RES_VIEW_FORMAT_UNSIGNED_BC3 - Block compressed 3
• RES_VIEW_FORMAT_UNSIGNED_BC4 - Block compressed 4 unsigned
• RES_VIEW_FORMAT_SIGNED_BC4 - Block compressed 4 signed
• RES_VIEW_FORMAT_UNSIGNED_BC5 - Block compressed 5 unsigned
• RES_VIEW_FORMAT_SIGNED_BC5 - Block compressed 5 signed
• RES_VIEW_FORMAT_UNSIGNED_BC6H - Block compressed 6 unsigned half-float
• RES_VIEW_FORMAT_SIGNED_BC6H - Block compressed 6 signed half-float
• RES_VIEW_FORMAT_UNSIGNED_BC7 - Block compressed 7

See Also:

• Constant Field Values

CU_RES_VIEW_FORMAT_SIGNED_BC6H

public static final int CU_RES_VIEW_FORMAT_SIGNED_BC6H

Resource view format. (CUresourceViewFormat)

Enum values:

• RES_VIEW_FORMAT_NONE - No resource view format (use underlying resource format)
• RES_VIEW_FORMAT_UINT_1X8 - 1 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_UINT_2X8 - 2 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_UINT_4X8 - 4 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_SINT_1X8 - 1 channel signed 8-bit integers
• RES_VIEW_FORMAT_SINT_2X8 - 2 channel signed 8-bit integers
• RES_VIEW_FORMAT_SINT_4X8 - 4 channel signed 8-bit integers
• RES_VIEW_FORMAT_UINT_1X16 - 1 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_UINT_2X16 - 2 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_UINT_4X16 - 4 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_SINT_1X16 - 1 channel signed 16-bit integers
• RES_VIEW_FORMAT_SINT_2X16 - 2 channel signed 16-bit integers
• RES_VIEW_FORMAT_SINT_4X16 - 4 channel signed 16-bit integers
• RES_VIEW_FORMAT_UINT_1X32 - 1 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_UINT_2X32 - 2 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_UINT_4X32 - 4 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_SINT_1X32 - 1 channel signed 32-bit integers
• RES_VIEW_FORMAT_SINT_2X32 - 2 channel signed 32-bit integers
• RES_VIEW_FORMAT_SINT_4X32 - 4 channel signed 32-bit integers
• RES_VIEW_FORMAT_FLOAT_1X16 - 1 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_2X16 - 2 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_4X16 - 4 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_1X32 - 1 channel 32-bit floating point
• RES_VIEW_FORMAT_FLOAT_2X32 - 2 channel 32-bit floating point
• RES_VIEW_FORMAT_FLOAT_4X32 - 4 channel 32-bit floating point
• RES_VIEW_FORMAT_UNSIGNED_BC1 - Block compressed 1
• RES_VIEW_FORMAT_UNSIGNED_BC2 - Block compressed 2
• RES_VIEW_FORMAT_UNSIGNED_BC3 - Block compressed 3
• RES_VIEW_FORMAT_UNSIGNED_BC4 - Block compressed 4 unsigned
• RES_VIEW_FORMAT_SIGNED_BC4 - Block compressed 4 signed
• RES_VIEW_FORMAT_UNSIGNED_BC5 - Block compressed 5 unsigned
• RES_VIEW_FORMAT_SIGNED_BC5 - Block compressed 5 signed
• RES_VIEW_FORMAT_UNSIGNED_BC6H - Block compressed 6 unsigned half-float
• RES_VIEW_FORMAT_SIGNED_BC6H - Block compressed 6 signed half-float
• RES_VIEW_FORMAT_UNSIGNED_BC7 - Block compressed 7

See Also:

• Constant Field Values

CU_RES_VIEW_FORMAT_UNSIGNED_BC7

public static final int CU_RES_VIEW_FORMAT_UNSIGNED_BC7

Resource view format. (CUresourceViewFormat)

Enum values:

• RES_VIEW_FORMAT_NONE - No resource view format (use underlying resource format)
• RES_VIEW_FORMAT_UINT_1X8 - 1 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_UINT_2X8 - 2 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_UINT_4X8 - 4 channel unsigned 8-bit integers
• RES_VIEW_FORMAT_SINT_1X8 - 1 channel signed 8-bit integers
• RES_VIEW_FORMAT_SINT_2X8 - 2 channel signed 8-bit integers
• RES_VIEW_FORMAT_SINT_4X8 - 4 channel signed 8-bit integers
• RES_VIEW_FORMAT_UINT_1X16 - 1 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_UINT_2X16 - 2 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_UINT_4X16 - 4 channel unsigned 16-bit integers
• RES_VIEW_FORMAT_SINT_1X16 - 1 channel signed 16-bit integers
• RES_VIEW_FORMAT_SINT_2X16 - 2 channel signed 16-bit integers
• RES_VIEW_FORMAT_SINT_4X16 - 4 channel signed 16-bit integers
• RES_VIEW_FORMAT_UINT_1X32 - 1 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_UINT_2X32 - 2 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_UINT_4X32 - 4 channel unsigned 32-bit integers
• RES_VIEW_FORMAT_SINT_1X32 - 1 channel signed 32-bit integers
• RES_VIEW_FORMAT_SINT_2X32 - 2 channel signed 32-bit integers
• RES_VIEW_FORMAT_SINT_4X32 - 4 channel signed 32-bit integers
• RES_VIEW_FORMAT_FLOAT_1X16 - 1 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_2X16 - 2 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_4X16 - 4 channel 16-bit floating point
• RES_VIEW_FORMAT_FLOAT_1X32 - 1 channel 32-bit floating point
• RES_VIEW_FORMAT_FLOAT_2X32 - 2 channel 32-bit floating point
• RES_VIEW_FORMAT_FLOAT_4X32 - 4 channel 32-bit floating point
• RES_VIEW_FORMAT_UNSIGNED_BC1 - Block compressed 1
• RES_VIEW_FORMAT_UNSIGNED_BC2 - Block compressed 2
• RES_VIEW_FORMAT_UNSIGNED_BC3 - Block compressed 3
• RES_VIEW_FORMAT_UNSIGNED_BC4 - Block compressed 4 unsigned
• RES_VIEW_FORMAT_SIGNED_BC4 - Block compressed 4 signed
• RES_VIEW_FORMAT_UNSIGNED_BC5 - Block compressed 5 unsigned
• RES_VIEW_FORMAT_SIGNED_BC5 - Block compressed 5 signed
• RES_VIEW_FORMAT_UNSIGNED_BC6H - Block compressed 6 unsigned half-float
• RES_VIEW_FORMAT_SIGNED_BC6H - Block compressed 6 signed half-float
• RES_VIEW_FORMAT_UNSIGNED_BC7 - Block compressed 7

See Also:

• Constant Field Values

CU_POINTER_ATTRIBUTE_ACCESS_FLAG_NONE

public static final int CU_POINTER_ATTRIBUTE_ACCESS_FLAG_NONE

Access flags that specify the level of access the current context's device has on the memory referenced. (CUDA_POINTER_ATTRIBUTE_ACCESS_FLAGS)

Enum values:

• POINTER_ATTRIBUTE_ACCESS_FLAG_NONE - No access, meaning the device cannot access this memory at all, thus must be staged through accessible memory in order to complete certain operations
• POINTER_ATTRIBUTE_ACCESS_FLAG_READ - Read-only access, meaning writes to this memory are considered invalid accesses and thus return error in that case.
• POINTER_ATTRIBUTE_ACCESS_FLAG_READWRITE - Read-write access, the device has full read-write access to the memory

See Also:

• Constant Field Values

CU_POINTER_ATTRIBUTE_ACCESS_FLAG_READ

public static final int CU_POINTER_ATTRIBUTE_ACCESS_FLAG_READ

Access flags that specify the level of access the current context's device has on the memory referenced. (CUDA_POINTER_ATTRIBUTE_ACCESS_FLAGS)

Enum values:

• POINTER_ATTRIBUTE_ACCESS_FLAG_NONE - No access, meaning the device cannot access this memory at all, thus must be staged through accessible memory in order to complete certain operations
• POINTER_ATTRIBUTE_ACCESS_FLAG_READ - Read-only access, meaning writes to this memory are considered invalid accesses and thus return error in that case.
• POINTER_ATTRIBUTE_ACCESS_FLAG_READWRITE - Read-write access, the device has full read-write access to the memory

See Also:

• Constant Field Values

CU_POINTER_ATTRIBUTE_ACCESS_FLAG_READWRITE

public static final int CU_POINTER_ATTRIBUTE_ACCESS_FLAG_READWRITE

Access flags that specify the level of access the current context's device has on the memory referenced. (CUDA_POINTER_ATTRIBUTE_ACCESS_FLAGS)

Enum values:

• POINTER_ATTRIBUTE_ACCESS_FLAG_NONE - No access, meaning the device cannot access this memory at all, thus must be staged through accessible memory in order to complete certain operations
• POINTER_ATTRIBUTE_ACCESS_FLAG_READ - Read-only access, meaning writes to this memory are considered invalid accesses and thus return error in that case.
• POINTER_ATTRIBUTE_ACCESS_FLAG_READWRITE - Read-write access, the device has full read-write access to the memory

See Also:

• Constant Field Values

CU_EXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_FD

public static final int CU_EXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_FD

External memory handle types. (CUexternalMemoryHandleType)

Enum values:

• EXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_FD - Handle is an opaque file descriptor
• EXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_WIN32 - Handle is an opaque shared NT handle
• EXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_WIN32_KMT - Handle is an opaque, globally shared handle
• EXTERNAL_MEMORY_HANDLE_TYPE_D3D12_HEAP - Handle is a D3D12 heap object
• EXTERNAL_MEMORY_HANDLE_TYPE_D3D12_RESOURCE - Handle is a D3D12 committed resource
• EXTERNAL_MEMORY_HANDLE_TYPE_D3D11_RESOURCE - Handle is a shared NT handle to a D3D11 resource
• EXTERNAL_MEMORY_HANDLE_TYPE_D3D11_RESOURCE_KMT - Handle is a globally shared handle to a D3D11 resource
• EXTERNAL_MEMORY_HANDLE_TYPE_NVSCIBUF - Handle is an NvSciBuf object

See Also:

• Constant Field Values

CU_EXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_WIN32

public static final int CU_EXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_WIN32

External memory handle types. (CUexternalMemoryHandleType)

Enum values:

• EXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_FD - Handle is an opaque file descriptor
• EXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_WIN32 - Handle is an opaque shared NT handle
• EXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_WIN32_KMT - Handle is an opaque, globally shared handle
• EXTERNAL_MEMORY_HANDLE_TYPE_D3D12_HEAP - Handle is a D3D12 heap object
• EXTERNAL_MEMORY_HANDLE_TYPE_D3D12_RESOURCE - Handle is a D3D12 committed resource
• EXTERNAL_MEMORY_HANDLE_TYPE_D3D11_RESOURCE - Handle is a shared NT handle to a D3D11 resource
• EXTERNAL_MEMORY_HANDLE_TYPE_D3D11_RESOURCE_KMT - Handle is a globally shared handle to a D3D11 resource
• EXTERNAL_MEMORY_HANDLE_TYPE_NVSCIBUF - Handle is an NvSciBuf object

See Also:

• Constant Field Values

CU_EXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_WIN32_KMT

public static final int CU_EXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_WIN32_KMT

External memory handle types. (CUexternalMemoryHandleType)

Enum values:

• EXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_FD - Handle is an opaque file descriptor
• EXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_WIN32 - Handle is an opaque shared NT handle
• EXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_WIN32_KMT - Handle is an opaque, globally shared handle
• EXTERNAL_MEMORY_HANDLE_TYPE_D3D12_HEAP - Handle is a D3D12 heap object
• EXTERNAL_MEMORY_HANDLE_TYPE_D3D12_RESOURCE - Handle is a D3D12 committed resource
• EXTERNAL_MEMORY_HANDLE_TYPE_D3D11_RESOURCE - Handle is a shared NT handle to a D3D11 resource
• EXTERNAL_MEMORY_HANDLE_TYPE_D3D11_RESOURCE_KMT - Handle is a globally shared handle to a D3D11 resource
• EXTERNAL_MEMORY_HANDLE_TYPE_NVSCIBUF - Handle is an NvSciBuf object

See Also:

• Constant Field Values

CU_EXTERNAL_MEMORY_HANDLE_TYPE_D3D12_HEAP

public static final int CU_EXTERNAL_MEMORY_HANDLE_TYPE_D3D12_HEAP

External memory handle types. (CUexternalMemoryHandleType)

Enum values:

• EXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_FD - Handle is an opaque file descriptor
• EXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_WIN32 - Handle is an opaque shared NT handle
• EXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_WIN32_KMT - Handle is an opaque, globally shared handle
• EXTERNAL_MEMORY_HANDLE_TYPE_D3D12_HEAP - Handle is a D3D12 heap object
• EXTERNAL_MEMORY_HANDLE_TYPE_D3D12_RESOURCE - Handle is a D3D12 committed resource
• EXTERNAL_MEMORY_HANDLE_TYPE_D3D11_RESOURCE - Handle is a shared NT handle to a D3D11 resource
• EXTERNAL_MEMORY_HANDLE_TYPE_D3D11_RESOURCE_KMT - Handle is a globally shared handle to a D3D11 resource
• EXTERNAL_MEMORY_HANDLE_TYPE_NVSCIBUF - Handle is an NvSciBuf object

See Also:

• Constant Field Values

CU_EXTERNAL_MEMORY_HANDLE_TYPE_D3D12_RESOURCE

public static final int CU_EXTERNAL_MEMORY_HANDLE_TYPE_D3D12_RESOURCE

External memory handle types. (CUexternalMemoryHandleType)

Enum values:

• EXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_FD - Handle is an opaque file descriptor
• EXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_WIN32 - Handle is an opaque shared NT handle
• EXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_WIN32_KMT - Handle is an opaque, globally shared handle
• EXTERNAL_MEMORY_HANDLE_TYPE_D3D12_HEAP - Handle is a D3D12 heap object
• EXTERNAL_MEMORY_HANDLE_TYPE_D3D12_RESOURCE - Handle is a D3D12 committed resource
• EXTERNAL_MEMORY_HANDLE_TYPE_D3D11_RESOURCE - Handle is a shared NT handle to a D3D11 resource
• EXTERNAL_MEMORY_HANDLE_TYPE_D3D11_RESOURCE_KMT - Handle is a globally shared handle to a D3D11 resource
• EXTERNAL_MEMORY_HANDLE_TYPE_NVSCIBUF - Handle is an NvSciBuf object

See Also:

• Constant Field Values

CU_EXTERNAL_MEMORY_HANDLE_TYPE_D3D11_RESOURCE

public static final int CU_EXTERNAL_MEMORY_HANDLE_TYPE_D3D11_RESOURCE

External memory handle types. (CUexternalMemoryHandleType)

Enum values:

• EXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_FD - Handle is an opaque file descriptor
• EXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_WIN32 - Handle is an opaque shared NT handle
• EXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_WIN32_KMT - Handle is an opaque, globally shared handle
• EXTERNAL_MEMORY_HANDLE_TYPE_D3D12_HEAP - Handle is a D3D12 heap object
• EXTERNAL_MEMORY_HANDLE_TYPE_D3D12_RESOURCE - Handle is a D3D12 committed resource
• EXTERNAL_MEMORY_HANDLE_TYPE_D3D11_RESOURCE - Handle is a shared NT handle to a D3D11 resource
• EXTERNAL_MEMORY_HANDLE_TYPE_D3D11_RESOURCE_KMT - Handle is a globally shared handle to a D3D11 resource
• EXTERNAL_MEMORY_HANDLE_TYPE_NVSCIBUF - Handle is an NvSciBuf object

See Also:

• Constant Field Values

CU_EXTERNAL_MEMORY_HANDLE_TYPE_D3D11_RESOURCE_KMT

public static final int CU_EXTERNAL_MEMORY_HANDLE_TYPE_D3D11_RESOURCE_KMT

External memory handle types. (CUexternalMemoryHandleType)

Enum values:

• EXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_FD - Handle is an opaque file descriptor
• EXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_WIN32 - Handle is an opaque shared NT handle
• EXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_WIN32_KMT - Handle is an opaque, globally shared handle
• EXTERNAL_MEMORY_HANDLE_TYPE_D3D12_HEAP - Handle is a D3D12 heap object
• EXTERNAL_MEMORY_HANDLE_TYPE_D3D12_RESOURCE - Handle is a D3D12 committed resource
• EXTERNAL_MEMORY_HANDLE_TYPE_D3D11_RESOURCE - Handle is a shared NT handle to a D3D11 resource
• EXTERNAL_MEMORY_HANDLE_TYPE_D3D11_RESOURCE_KMT - Handle is a globally shared handle to a D3D11 resource
• EXTERNAL_MEMORY_HANDLE_TYPE_NVSCIBUF - Handle is an NvSciBuf object

See Also:

• Constant Field Values

CU_EXTERNAL_MEMORY_HANDLE_TYPE_NVSCIBUF

public static final int CU_EXTERNAL_MEMORY_HANDLE_TYPE_NVSCIBUF

External memory handle types. (CUexternalMemoryHandleType)

Enum values:

• EXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_FD - Handle is an opaque file descriptor
• EXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_WIN32 - Handle is an opaque shared NT handle
• EXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_WIN32_KMT - Handle is an opaque, globally shared handle
• EXTERNAL_MEMORY_HANDLE_TYPE_D3D12_HEAP - Handle is a D3D12 heap object
• EXTERNAL_MEMORY_HANDLE_TYPE_D3D12_RESOURCE - Handle is a D3D12 committed resource
• EXTERNAL_MEMORY_HANDLE_TYPE_D3D11_RESOURCE - Handle is a shared NT handle to a D3D11 resource
• EXTERNAL_MEMORY_HANDLE_TYPE_D3D11_RESOURCE_KMT - Handle is a globally shared handle to a D3D11 resource
• EXTERNAL_MEMORY_HANDLE_TYPE_NVSCIBUF - Handle is an NvSciBuf object

See Also:

• Constant Field Values

CUDA_EXTERNAL_MEMORY_DEDICATED

public static final int CUDA_EXTERNAL_MEMORY_DEDICATED

Indicates that the external memory object is a dedicated resource.

See Also:

• Constant Field Values

CUDA_EXTERNAL_SEMAPHORE_SIGNAL_SKIP_NVSCIBUF_MEMSYNC

public static final int CUDA_EXTERNAL_SEMAPHORE_SIGNAL_SKIP_NVSCIBUF_MEMSYNC

When the flags parameter of CUDA_EXTERNAL_SEMAPHORE_SIGNAL_PARAMS contains this flag, it indicates that signaling an external semaphore object should skip performing appropriate memory synchronization operations over all the external memory objects that are imported as EXTERNAL_MEMORY_HANDLE_TYPE_NVSCIBUF, which otherwise are performed by default to ensure data coherency with other importers of the same NvSciBuf memory objects.

See Also:

• Constant Field Values

CUDA_EXTERNAL_SEMAPHORE_WAIT_SKIP_NVSCIBUF_MEMSYNC

public static final int CUDA_EXTERNAL_SEMAPHORE_WAIT_SKIP_NVSCIBUF_MEMSYNC

When the flags parameter of CUDA_EXTERNAL_SEMAPHORE_WAIT_PARAMS contains this flag, it indicates that waiting on an external semaphore object should skip performing appropriate memory synchronization operations over all the external memory objects that are imported as EXTERNAL_MEMORY_HANDLE_TYPE_NVSCIBUF, which otherwise are performed by default to ensure data coherency with other importers of the same NvSciBuf memory objects.

See Also:

• Constant Field Values

CUDA_NVSCISYNC_ATTR_SIGNAL

public static final int CUDA_NVSCISYNC_ATTR_SIGNAL

When flags of DeviceGetNvSciSyncAttributes is set to this, it indicates that application needs signaler specific NvSciSyncAttr to be filled by cuDeviceGetNvSciSyncAttributes.

See Also:

• Constant Field Values

CUDA_NVSCISYNC_ATTR_WAIT

public static final int CUDA_NVSCISYNC_ATTR_WAIT

When flags of DeviceGetNvSciSyncAttributes is set to this, it indicates that application needs waiter specific NvSciSyncAttr to be filled by cuDeviceGetNvSciSyncAttributes.

See Also:

• Constant Field Values

CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_FD

public static final int CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_FD

External semaphore handle types. (CUexternalSemaphoreHandleType)

Enum values:

• EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_FD - Handle is an opaque file descriptor
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32 - Handle is an opaque shared NT handle
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32_KMT - Handle is an opaque, globally shared handle
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D12_FENCE - Handle is a shared NT handle referencing a D3D12 fence object
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_FENCE - Handle is a shared NT handle referencing a D3D11 fence object
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_NVSCISYNC - Opaque handle to NvSciSync Object
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEX - Handle is a shared NT handle referencing a D3D11 keyed mutex object
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEX_KMT - Handle is a globally shared handle referencing a D3D11 keyed mutex object
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_FD - Handle is an opaque file descriptor referencing a timeline semaphore
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_WIN32 - Handle is an opaque shared NT handle referencing a timeline semaphore

See Also:

• Constant Field Values

CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32

public static final int CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32

External semaphore handle types. (CUexternalSemaphoreHandleType)

Enum values:

• EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_FD - Handle is an opaque file descriptor
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32 - Handle is an opaque shared NT handle
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32_KMT - Handle is an opaque, globally shared handle
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D12_FENCE - Handle is a shared NT handle referencing a D3D12 fence object
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_FENCE - Handle is a shared NT handle referencing a D3D11 fence object
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_NVSCISYNC - Opaque handle to NvSciSync Object
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEX - Handle is a shared NT handle referencing a D3D11 keyed mutex object
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEX_KMT - Handle is a globally shared handle referencing a D3D11 keyed mutex object
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_FD - Handle is an opaque file descriptor referencing a timeline semaphore
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_WIN32 - Handle is an opaque shared NT handle referencing a timeline semaphore

See Also:

• Constant Field Values

CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32_KMT

public static final int CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32_KMT

External semaphore handle types. (CUexternalSemaphoreHandleType)

Enum values:

• EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_FD - Handle is an opaque file descriptor
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32 - Handle is an opaque shared NT handle
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32_KMT - Handle is an opaque, globally shared handle
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D12_FENCE - Handle is a shared NT handle referencing a D3D12 fence object
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_FENCE - Handle is a shared NT handle referencing a D3D11 fence object
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_NVSCISYNC - Opaque handle to NvSciSync Object
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEX - Handle is a shared NT handle referencing a D3D11 keyed mutex object
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEX_KMT - Handle is a globally shared handle referencing a D3D11 keyed mutex object
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_FD - Handle is an opaque file descriptor referencing a timeline semaphore
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_WIN32 - Handle is an opaque shared NT handle referencing a timeline semaphore

See Also:

• Constant Field Values

CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D12_FENCE

public static final int CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D12_FENCE

External semaphore handle types. (CUexternalSemaphoreHandleType)

Enum values:

• EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_FD - Handle is an opaque file descriptor
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32 - Handle is an opaque shared NT handle
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32_KMT - Handle is an opaque, globally shared handle
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D12_FENCE - Handle is a shared NT handle referencing a D3D12 fence object
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_FENCE - Handle is a shared NT handle referencing a D3D11 fence object
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_NVSCISYNC - Opaque handle to NvSciSync Object
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEX - Handle is a shared NT handle referencing a D3D11 keyed mutex object
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEX_KMT - Handle is a globally shared handle referencing a D3D11 keyed mutex object
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_FD - Handle is an opaque file descriptor referencing a timeline semaphore
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_WIN32 - Handle is an opaque shared NT handle referencing a timeline semaphore

See Also:

• Constant Field Values

CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_FENCE

public static final int CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_FENCE

External semaphore handle types. (CUexternalSemaphoreHandleType)

Enum values:

• EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_FD - Handle is an opaque file descriptor
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32 - Handle is an opaque shared NT handle
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32_KMT - Handle is an opaque, globally shared handle
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D12_FENCE - Handle is a shared NT handle referencing a D3D12 fence object
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_FENCE - Handle is a shared NT handle referencing a D3D11 fence object
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_NVSCISYNC - Opaque handle to NvSciSync Object
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEX - Handle is a shared NT handle referencing a D3D11 keyed mutex object
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEX_KMT - Handle is a globally shared handle referencing a D3D11 keyed mutex object
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_FD - Handle is an opaque file descriptor referencing a timeline semaphore
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_WIN32 - Handle is an opaque shared NT handle referencing a timeline semaphore

See Also:

• Constant Field Values

CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_NVSCISYNC

public static final int CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_NVSCISYNC

External semaphore handle types. (CUexternalSemaphoreHandleType)

Enum values:

• EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_FD - Handle is an opaque file descriptor
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32 - Handle is an opaque shared NT handle
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32_KMT - Handle is an opaque, globally shared handle
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D12_FENCE - Handle is a shared NT handle referencing a D3D12 fence object
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_FENCE - Handle is a shared NT handle referencing a D3D11 fence object
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_NVSCISYNC - Opaque handle to NvSciSync Object
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEX - Handle is a shared NT handle referencing a D3D11 keyed mutex object
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEX_KMT - Handle is a globally shared handle referencing a D3D11 keyed mutex object
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_FD - Handle is an opaque file descriptor referencing a timeline semaphore
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_WIN32 - Handle is an opaque shared NT handle referencing a timeline semaphore

See Also:

• Constant Field Values

CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEX

public static final int CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEX

External semaphore handle types. (CUexternalSemaphoreHandleType)

Enum values:

• EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_FD - Handle is an opaque file descriptor
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32 - Handle is an opaque shared NT handle
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32_KMT - Handle is an opaque, globally shared handle
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D12_FENCE - Handle is a shared NT handle referencing a D3D12 fence object
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_FENCE - Handle is a shared NT handle referencing a D3D11 fence object
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_NVSCISYNC - Opaque handle to NvSciSync Object
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEX - Handle is a shared NT handle referencing a D3D11 keyed mutex object
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEX_KMT - Handle is a globally shared handle referencing a D3D11 keyed mutex object
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_FD - Handle is an opaque file descriptor referencing a timeline semaphore
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_WIN32 - Handle is an opaque shared NT handle referencing a timeline semaphore

See Also:

• Constant Field Values

CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEX_KMT

public static final int CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEX_KMT

External semaphore handle types. (CUexternalSemaphoreHandleType)

Enum values:

• EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_FD - Handle is an opaque file descriptor
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32 - Handle is an opaque shared NT handle
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32_KMT - Handle is an opaque, globally shared handle
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D12_FENCE - Handle is a shared NT handle referencing a D3D12 fence object
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_FENCE - Handle is a shared NT handle referencing a D3D11 fence object
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_NVSCISYNC - Opaque handle to NvSciSync Object
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEX - Handle is a shared NT handle referencing a D3D11 keyed mutex object
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEX_KMT - Handle is a globally shared handle referencing a D3D11 keyed mutex object
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_FD - Handle is an opaque file descriptor referencing a timeline semaphore
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_WIN32 - Handle is an opaque shared NT handle referencing a timeline semaphore

See Also:

• Constant Field Values

CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_FD

public static final int CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_FD

External semaphore handle types. (CUexternalSemaphoreHandleType)

Enum values:

• EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_FD - Handle is an opaque file descriptor
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32 - Handle is an opaque shared NT handle
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32_KMT - Handle is an opaque, globally shared handle
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D12_FENCE - Handle is a shared NT handle referencing a D3D12 fence object
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_FENCE - Handle is a shared NT handle referencing a D3D11 fence object
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_NVSCISYNC - Opaque handle to NvSciSync Object
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEX - Handle is a shared NT handle referencing a D3D11 keyed mutex object
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEX_KMT - Handle is a globally shared handle referencing a D3D11 keyed mutex object
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_FD - Handle is an opaque file descriptor referencing a timeline semaphore
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_WIN32 - Handle is an opaque shared NT handle referencing a timeline semaphore

See Also:

• Constant Field Values

CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_WIN32

public static final int CU_EXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_WIN32

External semaphore handle types. (CUexternalSemaphoreHandleType)

Enum values:

• EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_FD - Handle is an opaque file descriptor
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32 - Handle is an opaque shared NT handle
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32_KMT - Handle is an opaque, globally shared handle
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D12_FENCE - Handle is a shared NT handle referencing a D3D12 fence object
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_FENCE - Handle is a shared NT handle referencing a D3D11 fence object
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_NVSCISYNC - Opaque handle to NvSciSync Object
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEX - Handle is a shared NT handle referencing a D3D11 keyed mutex object
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEX_KMT - Handle is a globally shared handle referencing a D3D11 keyed mutex object
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_FD - Handle is an opaque file descriptor referencing a timeline semaphore
• EXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_WIN32 - Handle is an opaque shared NT handle referencing a timeline semaphore

See Also:

• Constant Field Values

CU_MEM_HANDLE_TYPE_NONE

public static final int CU_MEM_HANDLE_TYPE_NONE

Flags for specifying particular handle types. (CUmemAllocationHandleType)

Enum values:

• MEM_HANDLE_TYPE_NONE - Does not allow any export mechanism.
• MEM_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR - Allows a file descriptor to be used for exporting. Permitted only on POSIX systems. (int)
• MEM_HANDLE_TYPE_WIN32 - Allows a Win32 NT handle to be used for exporting. (HANDLE)
• MEM_HANDLE_TYPE_WIN32_KMT - Allows a Win32 KMT handle to be used for exporting. (D3DKMT_HANDLE)

See Also:

• Constant Field Values

CU_MEM_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR

public static final int CU_MEM_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR

Flags for specifying particular handle types. (CUmemAllocationHandleType)

Enum values:

• MEM_HANDLE_TYPE_NONE - Does not allow any export mechanism.
• MEM_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR - Allows a file descriptor to be used for exporting. Permitted only on POSIX systems. (int)
• MEM_HANDLE_TYPE_WIN32 - Allows a Win32 NT handle to be used for exporting. (HANDLE)
• MEM_HANDLE_TYPE_WIN32_KMT - Allows a Win32 KMT handle to be used for exporting. (D3DKMT_HANDLE)

See Also:

• Constant Field Values

CU_MEM_HANDLE_TYPE_WIN32

public static final int CU_MEM_HANDLE_TYPE_WIN32

Flags for specifying particular handle types. (CUmemAllocationHandleType)

Enum values:

• MEM_HANDLE_TYPE_NONE - Does not allow any export mechanism.
• MEM_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR - Allows a file descriptor to be used for exporting. Permitted only on POSIX systems. (int)
• MEM_HANDLE_TYPE_WIN32 - Allows a Win32 NT handle to be used for exporting. (HANDLE)
• MEM_HANDLE_TYPE_WIN32_KMT - Allows a Win32 KMT handle to be used for exporting. (D3DKMT_HANDLE)

See Also:

• Constant Field Values

CU_MEM_HANDLE_TYPE_WIN32_KMT

public static final int CU_MEM_HANDLE_TYPE_WIN32_KMT

Flags for specifying particular handle types. (CUmemAllocationHandleType)

Enum values:

• MEM_HANDLE_TYPE_NONE - Does not allow any export mechanism.
• MEM_HANDLE_TYPE_POSIX_FILE_DESCRIPTOR - Allows a file descriptor to be used for exporting. Permitted only on POSIX systems. (int)
• MEM_HANDLE_TYPE_WIN32 - Allows a Win32 NT handle to be used for exporting. (HANDLE)
• MEM_HANDLE_TYPE_WIN32_KMT - Allows a Win32 KMT handle to be used for exporting. (D3DKMT_HANDLE)

See Also:

• Constant Field Values

CU_MEM_ACCESS_FLAGS_PROT_NONE

public static final int CU_MEM_ACCESS_FLAGS_PROT_NONE

Specifies the memory protection flags for mapping. (CUmemAccess_flags)

Enum values:

• MEM_ACCESS_FLAGS_PROT_NONE - Default, make the address range not accessible
• MEM_ACCESS_FLAGS_PROT_READ - Make the address range read accessible
• MEM_ACCESS_FLAGS_PROT_READWRITE - Make the address range read-write accessible

See Also:

• Constant Field Values

CU_MEM_ACCESS_FLAGS_PROT_READ

public static final int CU_MEM_ACCESS_FLAGS_PROT_READ

Specifies the memory protection flags for mapping. (CUmemAccess_flags)

Enum values:

• MEM_ACCESS_FLAGS_PROT_NONE - Default, make the address range not accessible
• MEM_ACCESS_FLAGS_PROT_READ - Make the address range read accessible
• MEM_ACCESS_FLAGS_PROT_READWRITE - Make the address range read-write accessible

See Also:

• Constant Field Values

CU_MEM_ACCESS_FLAGS_PROT_READWRITE

public static final int CU_MEM_ACCESS_FLAGS_PROT_READWRITE

Specifies the memory protection flags for mapping. (CUmemAccess_flags)

Enum values:

• MEM_ACCESS_FLAGS_PROT_NONE - Default, make the address range not accessible
• MEM_ACCESS_FLAGS_PROT_READ - Make the address range read accessible
• MEM_ACCESS_FLAGS_PROT_READWRITE - Make the address range read-write accessible

See Also:

• Constant Field Values

CU_MEM_LOCATION_TYPE_INVALID

public static final int CU_MEM_LOCATION_TYPE_INVALID

Specifies the type of location. (CUmemLocationType)

Enum values:

• MEM_LOCATION_TYPE_INVALID
• MEM_LOCATION_TYPE_DEVICE - Location is a device location, thus id is a device ordinal

See Also:

• Constant Field Values

CU_MEM_LOCATION_TYPE_DEVICE

public static final int CU_MEM_LOCATION_TYPE_DEVICE

Specifies the type of location. (CUmemLocationType)

Enum values:

• MEM_LOCATION_TYPE_INVALID
• MEM_LOCATION_TYPE_DEVICE - Location is a device location, thus id is a device ordinal

See Also:

• Constant Field Values

CU_MEM_ALLOCATION_TYPE_INVALID

public static final int CU_MEM_ALLOCATION_TYPE_INVALID

Defines the allocation types available. (CUmemAllocationType)

Enum values:

• MEM_ALLOCATION_TYPE_INVALID
• MEM_ALLOCATION_TYPE_PINNED - This allocation type is 'pinned', i.e. cannot migrate from its current location while the application is actively using it

See Also:

• Constant Field Values

CU_MEM_ALLOCATION_TYPE_PINNED

public static final int CU_MEM_ALLOCATION_TYPE_PINNED

Defines the allocation types available. (CUmemAllocationType)

Enum values:

• MEM_ALLOCATION_TYPE_INVALID
• MEM_ALLOCATION_TYPE_PINNED - This allocation type is 'pinned', i.e. cannot migrate from its current location while the application is actively using it

See Also:

• Constant Field Values

CU_MEM_ALLOC_GRANULARITY_MINIMUM

public static final int CU_MEM_ALLOC_GRANULARITY_MINIMUM

Flag for requesting different optimal and required granularities for an allocation. (CUmemAllocationGranularity_flags)

Enum values:

• MEM_ALLOC_GRANULARITY_MINIMUM - Minimum required granularity for allocation
• MEM_ALLOC_GRANULARITY_RECOMMENDED - Recommended granularity for allocation for best performance

See Also:

• Constant Field Values

CU_MEM_ALLOC_GRANULARITY_RECOMMENDED

public static final int CU_MEM_ALLOC_GRANULARITY_RECOMMENDED

Flag for requesting different optimal and required granularities for an allocation. (CUmemAllocationGranularity_flags)

Enum values:

• MEM_ALLOC_GRANULARITY_MINIMUM - Minimum required granularity for allocation
• MEM_ALLOC_GRANULARITY_RECOMMENDED - Recommended granularity for allocation for best performance

See Also:

• Constant Field Values

CU_ARRAY_SPARSE_SUBRESOURCE_TYPE_SPARSE_LEVEL

public static final int CU_ARRAY_SPARSE_SUBRESOURCE_TYPE_SPARSE_LEVEL

Sparse subresource types. (CUarraySparseSubresourceType)

Enum values:

• ARRAY_SPARSE_SUBRESOURCE_TYPE_SPARSE_LEVEL
• ARRAY_SPARSE_SUBRESOURCE_TYPE_MIPTAIL

See Also:

• Constant Field Values

CU_ARRAY_SPARSE_SUBRESOURCE_TYPE_MIPTAIL

public static final int CU_ARRAY_SPARSE_SUBRESOURCE_TYPE_MIPTAIL

Sparse subresource types. (CUarraySparseSubresourceType)

Enum values:

• ARRAY_SPARSE_SUBRESOURCE_TYPE_SPARSE_LEVEL
• ARRAY_SPARSE_SUBRESOURCE_TYPE_MIPTAIL

See Also:

• Constant Field Values

CU_MEM_OPERATION_TYPE_MAP

public static final int CU_MEM_OPERATION_TYPE_MAP

Memory operation types. (CUmemOperationType)

Enum values:

• MEM_OPERATION_TYPE_MAP
• MEM_OPERATION_TYPE_UNMAP

See Also:

• Constant Field Values

CU_MEM_OPERATION_TYPE_UNMAP

public static final int CU_MEM_OPERATION_TYPE_UNMAP

Memory operation types. (CUmemOperationType)

Enum values:

• MEM_OPERATION_TYPE_MAP
• MEM_OPERATION_TYPE_UNMAP

See Also:

• Constant Field Values

CU_MEM_HANDLE_TYPE_GENERIC

public static final int CU_MEM_HANDLE_TYPE_GENERIC

Memory handle types (CUmemHandleType)

See Also:

• Constant Field Values

CU_MEM_ALLOCATION_COMP_NONE

public static final int CU_MEM_ALLOCATION_COMP_NONE

Specifies compression attribute for an allocation. (CUmemAllocationCompType)

Enum values:

• MEM_ALLOCATION_COMP_NONE - Allocating non-compressible memory
• MEM_ALLOCATION_COMP_GENERIC - Allocating compressible memory

See Also:

• Constant Field Values

CU_MEM_ALLOCATION_COMP_GENERIC

public static final int CU_MEM_ALLOCATION_COMP_GENERIC

Specifies compression attribute for an allocation. (CUmemAllocationCompType)

Enum values:

• MEM_ALLOCATION_COMP_NONE - Allocating non-compressible memory
• MEM_ALLOCATION_COMP_GENERIC - Allocating compressible memory

See Also:

• Constant Field Values

CU_MEM_CREATE_USAGE_TILE_POOL

public static final int CU_MEM_CREATE_USAGE_TILE_POOL

This flag if set indicates that the memory will be used as a tile pool.

See Also:

• Constant Field Values

CU_GRAPH_EXEC_UPDATE_SUCCESS

public static final int CU_GRAPH_EXEC_UPDATE_SUCCESS

CUgraphExecUpdateResult

Enum values:

• GRAPH_EXEC_UPDATE_SUCCESS - The update succeeded
• GRAPH_EXEC_UPDATE_ERROR - The update failed for an unexpected reason which is described in the return value of the function
• GRAPH_EXEC_UPDATE_ERROR_TOPOLOGY_CHANGED - The update failed because the topology changed
• GRAPH_EXEC_UPDATE_ERROR_NODE_TYPE_CHANGED - The update failed because a node type changed
• GRAPH_EXEC_UPDATE_ERROR_FUNCTION_CHANGED - The update failed because the function of a kernel node changed (CUDA driver <11.2)
• GRAPH_EXEC_UPDATE_ERROR_PARAMETERS_CHANGED - The update failed because the parameters changed in a way that is not supported
• GRAPH_EXEC_UPDATE_ERROR_NOT_SUPPORTED - The update failed because something about the node is not supported
• GRAPH_EXEC_UPDATE_ERROR_UNSUPPORTED_FUNCTION_CHANGE - The update failed because the function of a kernel node changed in an unsupported way

See Also:

• Constant Field Values

CU_GRAPH_EXEC_UPDATE_ERROR

public static final int CU_GRAPH_EXEC_UPDATE_ERROR

CUgraphExecUpdateResult

Enum values:

• GRAPH_EXEC_UPDATE_SUCCESS - The update succeeded
• GRAPH_EXEC_UPDATE_ERROR - The update failed for an unexpected reason which is described in the return value of the function
• GRAPH_EXEC_UPDATE_ERROR_TOPOLOGY_CHANGED - The update failed because the topology changed
• GRAPH_EXEC_UPDATE_ERROR_NODE_TYPE_CHANGED - The update failed because a node type changed
• GRAPH_EXEC_UPDATE_ERROR_FUNCTION_CHANGED - The update failed because the function of a kernel node changed (CUDA driver <11.2)
• GRAPH_EXEC_UPDATE_ERROR_PARAMETERS_CHANGED - The update failed because the parameters changed in a way that is not supported
• GRAPH_EXEC_UPDATE_ERROR_NOT_SUPPORTED - The update failed because something about the node is not supported
• GRAPH_EXEC_UPDATE_ERROR_UNSUPPORTED_FUNCTION_CHANGE - The update failed because the function of a kernel node changed in an unsupported way

See Also:

• Constant Field Values

CU_GRAPH_EXEC_UPDATE_ERROR_TOPOLOGY_CHANGED

public static final int CU_GRAPH_EXEC_UPDATE_ERROR_TOPOLOGY_CHANGED

CUgraphExecUpdateResult

Enum values:

• GRAPH_EXEC_UPDATE_SUCCESS - The update succeeded
• GRAPH_EXEC_UPDATE_ERROR - The update failed for an unexpected reason which is described in the return value of the function
• GRAPH_EXEC_UPDATE_ERROR_TOPOLOGY_CHANGED - The update failed because the topology changed
• GRAPH_EXEC_UPDATE_ERROR_NODE_TYPE_CHANGED - The update failed because a node type changed
• GRAPH_EXEC_UPDATE_ERROR_FUNCTION_CHANGED - The update failed because the function of a kernel node changed (CUDA driver <11.2)
• GRAPH_EXEC_UPDATE_ERROR_PARAMETERS_CHANGED - The update failed because the parameters changed in a way that is not supported
• GRAPH_EXEC_UPDATE_ERROR_NOT_SUPPORTED - The update failed because something about the node is not supported
• GRAPH_EXEC_UPDATE_ERROR_UNSUPPORTED_FUNCTION_CHANGE - The update failed because the function of a kernel node changed in an unsupported way

See Also:

• Constant Field Values

CU_GRAPH_EXEC_UPDATE_ERROR_NODE_TYPE_CHANGED

public static final int CU_GRAPH_EXEC_UPDATE_ERROR_NODE_TYPE_CHANGED

CUgraphExecUpdateResult

Enum values:

• GRAPH_EXEC_UPDATE_SUCCESS - The update succeeded
• GRAPH_EXEC_UPDATE_ERROR - The update failed for an unexpected reason which is described in the return value of the function
• GRAPH_EXEC_UPDATE_ERROR_TOPOLOGY_CHANGED - The update failed because the topology changed
• GRAPH_EXEC_UPDATE_ERROR_NODE_TYPE_CHANGED - The update failed because a node type changed
• GRAPH_EXEC_UPDATE_ERROR_FUNCTION_CHANGED - The update failed because the function of a kernel node changed (CUDA driver <11.2)
• GRAPH_EXEC_UPDATE_ERROR_PARAMETERS_CHANGED - The update failed because the parameters changed in a way that is not supported
• GRAPH_EXEC_UPDATE_ERROR_NOT_SUPPORTED - The update failed because something about the node is not supported
• GRAPH_EXEC_UPDATE_ERROR_UNSUPPORTED_FUNCTION_CHANGE - The update failed because the function of a kernel node changed in an unsupported way

See Also:

• Constant Field Values

CU_GRAPH_EXEC_UPDATE_ERROR_FUNCTION_CHANGED

public static final int CU_GRAPH_EXEC_UPDATE_ERROR_FUNCTION_CHANGED

CUgraphExecUpdateResult

Enum values:

• GRAPH_EXEC_UPDATE_SUCCESS - The update succeeded
• GRAPH_EXEC_UPDATE_ERROR - The update failed for an unexpected reason which is described in the return value of the function
• GRAPH_EXEC_UPDATE_ERROR_TOPOLOGY_CHANGED - The update failed because the topology changed
• GRAPH_EXEC_UPDATE_ERROR_NODE_TYPE_CHANGED - The update failed because a node type changed
• GRAPH_EXEC_UPDATE_ERROR_FUNCTION_CHANGED - The update failed because the function of a kernel node changed (CUDA driver <11.2)
• GRAPH_EXEC_UPDATE_ERROR_PARAMETERS_CHANGED - The update failed because the parameters changed in a way that is not supported
• GRAPH_EXEC_UPDATE_ERROR_NOT_SUPPORTED - The update failed because something about the node is not supported
• GRAPH_EXEC_UPDATE_ERROR_UNSUPPORTED_FUNCTION_CHANGE - The update failed because the function of a kernel node changed in an unsupported way

See Also:

• Constant Field Values

CU_GRAPH_EXEC_UPDATE_ERROR_PARAMETERS_CHANGED

public static final int CU_GRAPH_EXEC_UPDATE_ERROR_PARAMETERS_CHANGED

CUgraphExecUpdateResult

Enum values:

• GRAPH_EXEC_UPDATE_SUCCESS - The update succeeded
• GRAPH_EXEC_UPDATE_ERROR - The update failed for an unexpected reason which is described in the return value of the function
• GRAPH_EXEC_UPDATE_ERROR_TOPOLOGY_CHANGED - The update failed because the topology changed
• GRAPH_EXEC_UPDATE_ERROR_NODE_TYPE_CHANGED - The update failed because a node type changed
• GRAPH_EXEC_UPDATE_ERROR_FUNCTION_CHANGED - The update failed because the function of a kernel node changed (CUDA driver <11.2)
• GRAPH_EXEC_UPDATE_ERROR_PARAMETERS_CHANGED - The update failed because the parameters changed in a way that is not supported
• GRAPH_EXEC_UPDATE_ERROR_NOT_SUPPORTED - The update failed because something about the node is not supported
• GRAPH_EXEC_UPDATE_ERROR_UNSUPPORTED_FUNCTION_CHANGE - The update failed because the function of a kernel node changed in an unsupported way

See Also:

• Constant Field Values

CU_GRAPH_EXEC_UPDATE_ERROR_NOT_SUPPORTED

public static final int CU_GRAPH_EXEC_UPDATE_ERROR_NOT_SUPPORTED

CUgraphExecUpdateResult

Enum values:

• GRAPH_EXEC_UPDATE_SUCCESS - The update succeeded
• GRAPH_EXEC_UPDATE_ERROR - The update failed for an unexpected reason which is described in the return value of the function
• GRAPH_EXEC_UPDATE_ERROR_TOPOLOGY_CHANGED - The update failed because the topology changed
• GRAPH_EXEC_UPDATE_ERROR_NODE_TYPE_CHANGED - The update failed because a node type changed
• GRAPH_EXEC_UPDATE_ERROR_FUNCTION_CHANGED - The update failed because the function of a kernel node changed (CUDA driver <11.2)
• GRAPH_EXEC_UPDATE_ERROR_PARAMETERS_CHANGED - The update failed because the parameters changed in a way that is not supported
• GRAPH_EXEC_UPDATE_ERROR_NOT_SUPPORTED - The update failed because something about the node is not supported
• GRAPH_EXEC_UPDATE_ERROR_UNSUPPORTED_FUNCTION_CHANGE - The update failed because the function of a kernel node changed in an unsupported way

See Also:

• Constant Field Values

CU_GRAPH_EXEC_UPDATE_ERROR_UNSUPPORTED_FUNCTION_CHANGE

public static final int CU_GRAPH_EXEC_UPDATE_ERROR_UNSUPPORTED_FUNCTION_CHANGE

CUgraphExecUpdateResult

Enum values:

• GRAPH_EXEC_UPDATE_SUCCESS - The update succeeded
• GRAPH_EXEC_UPDATE_ERROR - The update failed for an unexpected reason which is described in the return value of the function
• GRAPH_EXEC_UPDATE_ERROR_TOPOLOGY_CHANGED - The update failed because the topology changed
• GRAPH_EXEC_UPDATE_ERROR_NODE_TYPE_CHANGED - The update failed because a node type changed
• GRAPH_EXEC_UPDATE_ERROR_FUNCTION_CHANGED - The update failed because the function of a kernel node changed (CUDA driver <11.2)
• GRAPH_EXEC_UPDATE_ERROR_PARAMETERS_CHANGED - The update failed because the parameters changed in a way that is not supported
• GRAPH_EXEC_UPDATE_ERROR_NOT_SUPPORTED - The update failed because something about the node is not supported
• GRAPH_EXEC_UPDATE_ERROR_UNSUPPORTED_FUNCTION_CHANGE - The update failed because the function of a kernel node changed in an unsupported way

See Also:

• Constant Field Values

CU_MEMPOOL_ATTR_REUSE_FOLLOW_EVENT_DEPENDENCIES

public static final int CU_MEMPOOL_ATTR_REUSE_FOLLOW_EVENT_DEPENDENCIES

CUDA memory pool attributes (CUmemPool_attribute)

Enum values:

• MEMPOOL_ATTR_REUSE_FOLLOW_EVENT_DEPENDENCIES - Allow MemAllocAsync to use memory asynchronously freed in another streams as long as a stream ordering dependency of the allocating stream on the free action exists. Cuda events and null stream interactions can create the required stream ordered dependencies.

  (value type = int, default enabled)

• MEMPOOL_ATTR_REUSE_ALLOW_OPPORTUNISTIC - Allow reuse of already completed frees when there is no dependency between the free and allocation. (value type = int, default enabled)
• MEMPOOL_ATTR_REUSE_ALLOW_INTERNAL_DEPENDENCIES - Allow MemAllocAsync to insert new stream dependencies in order to establish the stream ordering required to reuse a piece of memory released by MemFreeAsync.

  (value type = int, default enabled).

• MEMPOOL_ATTR_RELEASE_THRESHOLD - Amount of reserved memory in bytes to hold onto before trying to release memory back to the OS.

  When more than the release threshold bytes of memory are held by the memory pool, the allocator will try to release memory back to the OS on the next call to stream, event or context synchronize.

  (value type = cuuint64_t, default 0)

• MEMPOOL_ATTR_RESERVED_MEM_CURRENT - Amount of backing memory currently allocated for the mempool. (value type = cuuint64_t)
• MEMPOOL_ATTR_RESERVED_MEM_HIGH - High watermark of backing memory allocated for the mempool since the last time it was reset. High watermark can only be reset to zero.

  (value type = cuuint64_t)

• MEMPOOL_ATTR_USED_MEM_CURRENT - Amount of memory from the pool that is currently in use by the application (value type = cuuint64_t).
• MEMPOOL_ATTR_USED_MEM_HIGH - High watermark of the amount of memory from the pool that was in use by the application since the last time it was reset. High watermark can only be reset to zero.

  (value type = cuuint64_t)

See Also:

• Constant Field Values

CU_MEMPOOL_ATTR_REUSE_ALLOW_OPPORTUNISTIC

public static final int CU_MEMPOOL_ATTR_REUSE_ALLOW_OPPORTUNISTIC

CUDA memory pool attributes (CUmemPool_attribute)

Enum values:

• MEMPOOL_ATTR_REUSE_FOLLOW_EVENT_DEPENDENCIES - Allow MemAllocAsync to use memory asynchronously freed in another streams as long as a stream ordering dependency of the allocating stream on the free action exists. Cuda events and null stream interactions can create the required stream ordered dependencies.

  (value type = int, default enabled)

• MEMPOOL_ATTR_REUSE_ALLOW_OPPORTUNISTIC - Allow reuse of already completed frees when there is no dependency between the free and allocation. (value type = int, default enabled)
• MEMPOOL_ATTR_REUSE_ALLOW_INTERNAL_DEPENDENCIES - Allow MemAllocAsync to insert new stream dependencies in order to establish the stream ordering required to reuse a piece of memory released by MemFreeAsync.

  (value type = int, default enabled).

• MEMPOOL_ATTR_RELEASE_THRESHOLD - Amount of reserved memory in bytes to hold onto before trying to release memory back to the OS.

  When more than the release threshold bytes of memory are held by the memory pool, the allocator will try to release memory back to the OS on the next call to stream, event or context synchronize.

  (value type = cuuint64_t, default 0)

• MEMPOOL_ATTR_RESERVED_MEM_CURRENT - Amount of backing memory currently allocated for the mempool. (value type = cuuint64_t)
• MEMPOOL_ATTR_RESERVED_MEM_HIGH - High watermark of backing memory allocated for the mempool since the last time it was reset. High watermark can only be reset to zero.

  (value type = cuuint64_t)

• MEMPOOL_ATTR_USED_MEM_CURRENT - Amount of memory from the pool that is currently in use by the application (value type = cuuint64_t).
• MEMPOOL_ATTR_USED_MEM_HIGH - High watermark of the amount of memory from the pool that was in use by the application since the last time it was reset. High watermark can only be reset to zero.

  (value type = cuuint64_t)

See Also:

• Constant Field Values

CU_MEMPOOL_ATTR_REUSE_ALLOW_INTERNAL_DEPENDENCIES

public static final int CU_MEMPOOL_ATTR_REUSE_ALLOW_INTERNAL_DEPENDENCIES

CUDA memory pool attributes (CUmemPool_attribute)

Enum values:

• MEMPOOL_ATTR_REUSE_FOLLOW_EVENT_DEPENDENCIES - Allow MemAllocAsync to use memory asynchronously freed in another streams as long as a stream ordering dependency of the allocating stream on the free action exists. Cuda events and null stream interactions can create the required stream ordered dependencies.

  (value type = int, default enabled)

• MEMPOOL_ATTR_REUSE_ALLOW_OPPORTUNISTIC - Allow reuse of already completed frees when there is no dependency between the free and allocation. (value type = int, default enabled)
• MEMPOOL_ATTR_REUSE_ALLOW_INTERNAL_DEPENDENCIES - Allow MemAllocAsync to insert new stream dependencies in order to establish the stream ordering required to reuse a piece of memory released by MemFreeAsync.

  (value type = int, default enabled).

• MEMPOOL_ATTR_RELEASE_THRESHOLD - Amount of reserved memory in bytes to hold onto before trying to release memory back to the OS.

  When more than the release threshold bytes of memory are held by the memory pool, the allocator will try to release memory back to the OS on the next call to stream, event or context synchronize.

  (value type = cuuint64_t, default 0)

• MEMPOOL_ATTR_RESERVED_MEM_CURRENT - Amount of backing memory currently allocated for the mempool. (value type = cuuint64_t)
• MEMPOOL_ATTR_RESERVED_MEM_HIGH - High watermark of backing memory allocated for the mempool since the last time it was reset. High watermark can only be reset to zero.

  (value type = cuuint64_t)

• MEMPOOL_ATTR_USED_MEM_CURRENT - Amount of memory from the pool that is currently in use by the application (value type = cuuint64_t).
• MEMPOOL_ATTR_USED_MEM_HIGH - High watermark of the amount of memory from the pool that was in use by the application since the last time it was reset. High watermark can only be reset to zero.

  (value type = cuuint64_t)

See Also:

• Constant Field Values

CU_MEMPOOL_ATTR_RELEASE_THRESHOLD

public static final int CU_MEMPOOL_ATTR_RELEASE_THRESHOLD

CUDA memory pool attributes (CUmemPool_attribute)

Enum values:

• MEMPOOL_ATTR_REUSE_FOLLOW_EVENT_DEPENDENCIES - Allow MemAllocAsync to use memory asynchronously freed in another streams as long as a stream ordering dependency of the allocating stream on the free action exists. Cuda events and null stream interactions can create the required stream ordered dependencies.

  (value type = int, default enabled)

• MEMPOOL_ATTR_REUSE_ALLOW_OPPORTUNISTIC - Allow reuse of already completed frees when there is no dependency between the free and allocation. (value type = int, default enabled)
• MEMPOOL_ATTR_REUSE_ALLOW_INTERNAL_DEPENDENCIES - Allow MemAllocAsync to insert new stream dependencies in order to establish the stream ordering required to reuse a piece of memory released by MemFreeAsync.

  (value type = int, default enabled).

• MEMPOOL_ATTR_RELEASE_THRESHOLD - Amount of reserved memory in bytes to hold onto before trying to release memory back to the OS.

  When more than the release threshold bytes of memory are held by the memory pool, the allocator will try to release memory back to the OS on the next call to stream, event or context synchronize.

  (value type = cuuint64_t, default 0)

• MEMPOOL_ATTR_RESERVED_MEM_CURRENT - Amount of backing memory currently allocated for the mempool. (value type = cuuint64_t)
• MEMPOOL_ATTR_RESERVED_MEM_HIGH - High watermark of backing memory allocated for the mempool since the last time it was reset. High watermark can only be reset to zero.

  (value type = cuuint64_t)

• MEMPOOL_ATTR_USED_MEM_CURRENT - Amount of memory from the pool that is currently in use by the application (value type = cuuint64_t).
• MEMPOOL_ATTR_USED_MEM_HIGH - High watermark of the amount of memory from the pool that was in use by the application since the last time it was reset. High watermark can only be reset to zero.

  (value type = cuuint64_t)

See Also:

• Constant Field Values

CU_MEMPOOL_ATTR_RESERVED_MEM_CURRENT

public static final int CU_MEMPOOL_ATTR_RESERVED_MEM_CURRENT

CUDA memory pool attributes (CUmemPool_attribute)

Enum values:

• MEMPOOL_ATTR_REUSE_FOLLOW_EVENT_DEPENDENCIES - Allow MemAllocAsync to use memory asynchronously freed in another streams as long as a stream ordering dependency of the allocating stream on the free action exists. Cuda events and null stream interactions can create the required stream ordered dependencies.

  (value type = int, default enabled)

• MEMPOOL_ATTR_REUSE_ALLOW_OPPORTUNISTIC - Allow reuse of already completed frees when there is no dependency between the free and allocation. (value type = int, default enabled)
• MEMPOOL_ATTR_REUSE_ALLOW_INTERNAL_DEPENDENCIES - Allow MemAllocAsync to insert new stream dependencies in order to establish the stream ordering required to reuse a piece of memory released by MemFreeAsync.

  (value type = int, default enabled).

• MEMPOOL_ATTR_RELEASE_THRESHOLD - Amount of reserved memory in bytes to hold onto before trying to release memory back to the OS.

  When more than the release threshold bytes of memory are held by the memory pool, the allocator will try to release memory back to the OS on the next call to stream, event or context synchronize.

  (value type = cuuint64_t, default 0)

• MEMPOOL_ATTR_RESERVED_MEM_CURRENT - Amount of backing memory currently allocated for the mempool. (value type = cuuint64_t)
• MEMPOOL_ATTR_RESERVED_MEM_HIGH - High watermark of backing memory allocated for the mempool since the last time it was reset. High watermark can only be reset to zero.

  (value type = cuuint64_t)

• MEMPOOL_ATTR_USED_MEM_CURRENT - Amount of memory from the pool that is currently in use by the application (value type = cuuint64_t).
• MEMPOOL_ATTR_USED_MEM_HIGH - High watermark of the amount of memory from the pool that was in use by the application since the last time it was reset. High watermark can only be reset to zero.

  (value type = cuuint64_t)

See Also:

• Constant Field Values

CU_MEMPOOL_ATTR_RESERVED_MEM_HIGH

public static final int CU_MEMPOOL_ATTR_RESERVED_MEM_HIGH

CUDA memory pool attributes (CUmemPool_attribute)

Enum values:

• MEMPOOL_ATTR_REUSE_FOLLOW_EVENT_DEPENDENCIES - Allow MemAllocAsync to use memory asynchronously freed in another streams as long as a stream ordering dependency of the allocating stream on the free action exists. Cuda events and null stream interactions can create the required stream ordered dependencies.

  (value type = int, default enabled)

• MEMPOOL_ATTR_REUSE_ALLOW_OPPORTUNISTIC - Allow reuse of already completed frees when there is no dependency between the free and allocation. (value type = int, default enabled)
• MEMPOOL_ATTR_REUSE_ALLOW_INTERNAL_DEPENDENCIES - Allow MemAllocAsync to insert new stream dependencies in order to establish the stream ordering required to reuse a piece of memory released by MemFreeAsync.

  (value type = int, default enabled).

• MEMPOOL_ATTR_RELEASE_THRESHOLD - Amount of reserved memory in bytes to hold onto before trying to release memory back to the OS.

  When more than the release threshold bytes of memory are held by the memory pool, the allocator will try to release memory back to the OS on the next call to stream, event or context synchronize.

  (value type = cuuint64_t, default 0)

• MEMPOOL_ATTR_RESERVED_MEM_CURRENT - Amount of backing memory currently allocated for the mempool. (value type = cuuint64_t)
• MEMPOOL_ATTR_RESERVED_MEM_HIGH - High watermark of backing memory allocated for the mempool since the last time it was reset. High watermark can only be reset to zero.

  (value type = cuuint64_t)

• MEMPOOL_ATTR_USED_MEM_CURRENT - Amount of memory from the pool that is currently in use by the application (value type = cuuint64_t).
• MEMPOOL_ATTR_USED_MEM_HIGH - High watermark of the amount of memory from the pool that was in use by the application since the last time it was reset. High watermark can only be reset to zero.

  (value type = cuuint64_t)

See Also:

• Constant Field Values

CU_MEMPOOL_ATTR_USED_MEM_CURRENT

public static final int CU_MEMPOOL_ATTR_USED_MEM_CURRENT

CUDA memory pool attributes (CUmemPool_attribute)

Enum values:

• MEMPOOL_ATTR_REUSE_FOLLOW_EVENT_DEPENDENCIES - Allow MemAllocAsync to use memory asynchronously freed in another streams as long as a stream ordering dependency of the allocating stream on the free action exists. Cuda events and null stream interactions can create the required stream ordered dependencies.

  (value type = int, default enabled)

• MEMPOOL_ATTR_REUSE_ALLOW_OPPORTUNISTIC - Allow reuse of already completed frees when there is no dependency between the free and allocation. (value type = int, default enabled)
• MEMPOOL_ATTR_REUSE_ALLOW_INTERNAL_DEPENDENCIES - Allow MemAllocAsync to insert new stream dependencies in order to establish the stream ordering required to reuse a piece of memory released by MemFreeAsync.

  (value type = int, default enabled).

• MEMPOOL_ATTR_RELEASE_THRESHOLD - Amount of reserved memory in bytes to hold onto before trying to release memory back to the OS.

  When more than the release threshold bytes of memory are held by the memory pool, the allocator will try to release memory back to the OS on the next call to stream, event or context synchronize.

  (value type = cuuint64_t, default 0)

• MEMPOOL_ATTR_RESERVED_MEM_CURRENT - Amount of backing memory currently allocated for the mempool. (value type = cuuint64_t)
• MEMPOOL_ATTR_RESERVED_MEM_HIGH - High watermark of backing memory allocated for the mempool since the last time it was reset. High watermark can only be reset to zero.

  (value type = cuuint64_t)

• MEMPOOL_ATTR_USED_MEM_CURRENT - Amount of memory from the pool that is currently in use by the application (value type = cuuint64_t).
• MEMPOOL_ATTR_USED_MEM_HIGH - High watermark of the amount of memory from the pool that was in use by the application since the last time it was reset. High watermark can only be reset to zero.

  (value type = cuuint64_t)

See Also:

• Constant Field Values

CU_MEMPOOL_ATTR_USED_MEM_HIGH

public static final int CU_MEMPOOL_ATTR_USED_MEM_HIGH

CUDA memory pool attributes (CUmemPool_attribute)

Enum values:

• MEMPOOL_ATTR_REUSE_FOLLOW_EVENT_DEPENDENCIES - Allow MemAllocAsync to use memory asynchronously freed in another streams as long as a stream ordering dependency of the allocating stream on the free action exists. Cuda events and null stream interactions can create the required stream ordered dependencies.

  (value type = int, default enabled)

• MEMPOOL_ATTR_REUSE_ALLOW_OPPORTUNISTIC - Allow reuse of already completed frees when there is no dependency between the free and allocation. (value type = int, default enabled)
• MEMPOOL_ATTR_REUSE_ALLOW_INTERNAL_DEPENDENCIES - Allow MemAllocAsync to insert new stream dependencies in order to establish the stream ordering required to reuse a piece of memory released by MemFreeAsync.

  (value type = int, default enabled).

• MEMPOOL_ATTR_RELEASE_THRESHOLD - Amount of reserved memory in bytes to hold onto before trying to release memory back to the OS.

  When more than the release threshold bytes of memory are held by the memory pool, the allocator will try to release memory back to the OS on the next call to stream, event or context synchronize.

  (value type = cuuint64_t, default 0)

• MEMPOOL_ATTR_RESERVED_MEM_CURRENT - Amount of backing memory currently allocated for the mempool. (value type = cuuint64_t)
• MEMPOOL_ATTR_RESERVED_MEM_HIGH - High watermark of backing memory allocated for the mempool since the last time it was reset. High watermark can only be reset to zero.

  (value type = cuuint64_t)

• MEMPOOL_ATTR_USED_MEM_CURRENT - Amount of memory from the pool that is currently in use by the application (value type = cuuint64_t).
• MEMPOOL_ATTR_USED_MEM_HIGH - High watermark of the amount of memory from the pool that was in use by the application since the last time it was reset. High watermark can only be reset to zero.

  (value type = cuuint64_t)

See Also:

• Constant Field Values

CU_GRAPH_MEM_ATTR_USED_MEM_CURRENT

public static final int CU_GRAPH_MEM_ATTR_USED_MEM_CURRENT

CUgraphMem_attribute

Enum values:

• GRAPH_MEM_ATTR_USED_MEM_CURRENT - (value type = cuuint64_t) Amount of memory, in bytes, currently associated with graphs
• GRAPH_MEM_ATTR_USED_MEM_HIGH - High watermark of memory, in bytes, associated with graphs since the last time it was reset. High watermark can only be reset to zero.

  (value type = cuuint64_t)

• GRAPH_MEM_ATTR_RESERVED_MEM_CURRENT - Amount of memory, in bytes, currently allocated for use by the CUDA graphs asynchronous allocator. (value type = cuuint64_t)
• GRAPH_MEM_ATTR_RESERVED_MEM_HIGH - High watermark of memory, in bytes, currently allocated for use by the CUDA graphs asynchronous allocator. (value type = cuuint64_t)

See Also:

• Constant Field Values

CU_GRAPH_MEM_ATTR_USED_MEM_HIGH

public static final int CU_GRAPH_MEM_ATTR_USED_MEM_HIGH

CUgraphMem_attribute

Enum values:

• GRAPH_MEM_ATTR_USED_MEM_CURRENT - (value type = cuuint64_t) Amount of memory, in bytes, currently associated with graphs
• GRAPH_MEM_ATTR_USED_MEM_HIGH - High watermark of memory, in bytes, associated with graphs since the last time it was reset. High watermark can only be reset to zero.

  (value type = cuuint64_t)

• GRAPH_MEM_ATTR_RESERVED_MEM_CURRENT - Amount of memory, in bytes, currently allocated for use by the CUDA graphs asynchronous allocator. (value type = cuuint64_t)
• GRAPH_MEM_ATTR_RESERVED_MEM_HIGH - High watermark of memory, in bytes, currently allocated for use by the CUDA graphs asynchronous allocator. (value type = cuuint64_t)

See Also:

• Constant Field Values

CU_GRAPH_MEM_ATTR_RESERVED_MEM_CURRENT

public static final int CU_GRAPH_MEM_ATTR_RESERVED_MEM_CURRENT

CUgraphMem_attribute

Enum values:

• GRAPH_MEM_ATTR_USED_MEM_CURRENT - (value type = cuuint64_t) Amount of memory, in bytes, currently associated with graphs
• GRAPH_MEM_ATTR_USED_MEM_HIGH - High watermark of memory, in bytes, associated with graphs since the last time it was reset. High watermark can only be reset to zero.

  (value type = cuuint64_t)

• GRAPH_MEM_ATTR_RESERVED_MEM_CURRENT - Amount of memory, in bytes, currently allocated for use by the CUDA graphs asynchronous allocator. (value type = cuuint64_t)
• GRAPH_MEM_ATTR_RESERVED_MEM_HIGH - High watermark of memory, in bytes, currently allocated for use by the CUDA graphs asynchronous allocator. (value type = cuuint64_t)

See Also:

• Constant Field Values

CU_GRAPH_MEM_ATTR_RESERVED_MEM_HIGH

public static final int CU_GRAPH_MEM_ATTR_RESERVED_MEM_HIGH

CUgraphMem_attribute

Enum values:

• GRAPH_MEM_ATTR_USED_MEM_CURRENT - (value type = cuuint64_t) Amount of memory, in bytes, currently associated with graphs
• GRAPH_MEM_ATTR_USED_MEM_HIGH - High watermark of memory, in bytes, associated with graphs since the last time it was reset. High watermark can only be reset to zero.

  (value type = cuuint64_t)

• GRAPH_MEM_ATTR_RESERVED_MEM_CURRENT - Amount of memory, in bytes, currently allocated for use by the CUDA graphs asynchronous allocator. (value type = cuuint64_t)
• GRAPH_MEM_ATTR_RESERVED_MEM_HIGH - High watermark of memory, in bytes, currently allocated for use by the CUDA graphs asynchronous allocator. (value type = cuuint64_t)

See Also:

• Constant Field Values

CU_CUDA_COOPERATIVE_LAUNCH_MULTI_DEVICE_NO_PRE_LAUNCH_SYNC

public static final int CU_CUDA_COOPERATIVE_LAUNCH_MULTI_DEVICE_NO_PRE_LAUNCH_SYNC

Enum values:

• CUDA_COOPERATIVE_LAUNCH_MULTI_DEVICE_NO_PRE_LAUNCH_SYNC - If set, each kernel launched as part of LaunchCooperativeKernelMultiDevice only waits for prior work in the stream corresponding to that GPU to complete before the kernel begins execution.
• CUDA_COOPERATIVE_LAUNCH_MULTI_DEVICE_NO_POST_LAUNCH_SYNC - If set, any subsequent work pushed in a stream that participated in a call to LaunchCooperativeKernelMultiDevice will only wait for the kernel launched on the GPU corresponding to that stream to complete before it begins execution.

See Also:

• Constant Field Values

CU_CUDA_COOPERATIVE_LAUNCH_MULTI_DEVICE_NO_POST_LAUNCH_SYNC

public static final int CU_CUDA_COOPERATIVE_LAUNCH_MULTI_DEVICE_NO_POST_LAUNCH_SYNC

Enum values:

• CUDA_COOPERATIVE_LAUNCH_MULTI_DEVICE_NO_PRE_LAUNCH_SYNC - If set, each kernel launched as part of LaunchCooperativeKernelMultiDevice only waits for prior work in the stream corresponding to that GPU to complete before the kernel begins execution.
• CUDA_COOPERATIVE_LAUNCH_MULTI_DEVICE_NO_POST_LAUNCH_SYNC - If set, any subsequent work pushed in a stream that participated in a call to LaunchCooperativeKernelMultiDevice will only wait for the kernel launched on the GPU corresponding to that stream to complete before it begins execution.

See Also:

• Constant Field Values

CUDA_ARRAY3D_LAYERED

public static final int CUDA_ARRAY3D_LAYERED

Enum values:

• CUDA_ARRAY3D_LAYERED - If set, the CUDA array is a collection of layers, where each layer is either a 1D or a 2D array and the Depth member of CUDA_ARRAY3D_DESCRIPTOR specifies the number of layers, not the depth of a 3D array.
• CUDA_ARRAY3D_2DARRAY - Deprecated, use CUDA_ARRAY3D_LAYERED.
• CUDA_ARRAY3D_SURFACE_LDST - This flag must be set in order to bind a surface reference to the CUDA array.
• CUDA_ARRAY3D_CUBEMAP - If set, the CUDA array is a collection of six 2D arrays, representing faces of a cube. The width of such a CUDA array must be equal to its height, and Depth must be six. If CUDA_ARRAY3D_LAYERED flag is also set, then the CUDA array is a collection of cubemaps and Depth must be a multiple of six.
• CUDA_ARRAY3D_TEXTURE_GATHER - This flag must be set in order to perform texture gather operations on a CUDA array.
• CUDA_ARRAY3D_DEPTH_TEXTURE - This flag if set indicates that the CUDA array is a DEPTH_TEXTURE.
• CUDA_ARRAY3D_COLOR_ATTACHMENT - This flag indicates that the CUDA array may be bound as a color target in an external graphics API.
• CUDA_ARRAY3D_SPARSE - This flag if set indicates that the CUDA array or CUDA mipmapped array is a sparse CUDA array or CUDA mipmapped array respectively

See Also:

• Constant Field Values

CUDA_ARRAY3D_2DARRAY

public static final int CUDA_ARRAY3D_2DARRAY

Enum values:

• CUDA_ARRAY3D_LAYERED - If set, the CUDA array is a collection of layers, where each layer is either a 1D or a 2D array and the Depth member of CUDA_ARRAY3D_DESCRIPTOR specifies the number of layers, not the depth of a 3D array.
• CUDA_ARRAY3D_2DARRAY - Deprecated, use CUDA_ARRAY3D_LAYERED.
• CUDA_ARRAY3D_SURFACE_LDST - This flag must be set in order to bind a surface reference to the CUDA array.
• CUDA_ARRAY3D_CUBEMAP - If set, the CUDA array is a collection of six 2D arrays, representing faces of a cube. The width of such a CUDA array must be equal to its height, and Depth must be six. If CUDA_ARRAY3D_LAYERED flag is also set, then the CUDA array is a collection of cubemaps and Depth must be a multiple of six.
• CUDA_ARRAY3D_TEXTURE_GATHER - This flag must be set in order to perform texture gather operations on a CUDA array.
• CUDA_ARRAY3D_DEPTH_TEXTURE - This flag if set indicates that the CUDA array is a DEPTH_TEXTURE.
• CUDA_ARRAY3D_COLOR_ATTACHMENT - This flag indicates that the CUDA array may be bound as a color target in an external graphics API.
• CUDA_ARRAY3D_SPARSE - This flag if set indicates that the CUDA array or CUDA mipmapped array is a sparse CUDA array or CUDA mipmapped array respectively

See Also:

• Constant Field Values

CUDA_ARRAY3D_SURFACE_LDST

public static final int CUDA_ARRAY3D_SURFACE_LDST

Enum values:

• CUDA_ARRAY3D_LAYERED - If set, the CUDA array is a collection of layers, where each layer is either a 1D or a 2D array and the Depth member of CUDA_ARRAY3D_DESCRIPTOR specifies the number of layers, not the depth of a 3D array.
• CUDA_ARRAY3D_2DARRAY - Deprecated, use CUDA_ARRAY3D_LAYERED.
• CUDA_ARRAY3D_SURFACE_LDST - This flag must be set in order to bind a surface reference to the CUDA array.
• CUDA_ARRAY3D_CUBEMAP - If set, the CUDA array is a collection of six 2D arrays, representing faces of a cube. The width of such a CUDA array must be equal to its height, and Depth must be six. If CUDA_ARRAY3D_LAYERED flag is also set, then the CUDA array is a collection of cubemaps and Depth must be a multiple of six.
• CUDA_ARRAY3D_TEXTURE_GATHER - This flag must be set in order to perform texture gather operations on a CUDA array.
• CUDA_ARRAY3D_DEPTH_TEXTURE - This flag if set indicates that the CUDA array is a DEPTH_TEXTURE.
• CUDA_ARRAY3D_COLOR_ATTACHMENT - This flag indicates that the CUDA array may be bound as a color target in an external graphics API.
• CUDA_ARRAY3D_SPARSE - This flag if set indicates that the CUDA array or CUDA mipmapped array is a sparse CUDA array or CUDA mipmapped array respectively

See Also:

• Constant Field Values

CUDA_ARRAY3D_CUBEMAP

public static final int CUDA_ARRAY3D_CUBEMAP

Enum values:

• CUDA_ARRAY3D_LAYERED - If set, the CUDA array is a collection of layers, where each layer is either a 1D or a 2D array and the Depth member of CUDA_ARRAY3D_DESCRIPTOR specifies the number of layers, not the depth of a 3D array.
• CUDA_ARRAY3D_2DARRAY - Deprecated, use CUDA_ARRAY3D_LAYERED.
• CUDA_ARRAY3D_SURFACE_LDST - This flag must be set in order to bind a surface reference to the CUDA array.
• CUDA_ARRAY3D_CUBEMAP - If set, the CUDA array is a collection of six 2D arrays, representing faces of a cube. The width of such a CUDA array must be equal to its height, and Depth must be six. If CUDA_ARRAY3D_LAYERED flag is also set, then the CUDA array is a collection of cubemaps and Depth must be a multiple of six.
• CUDA_ARRAY3D_TEXTURE_GATHER - This flag must be set in order to perform texture gather operations on a CUDA array.
• CUDA_ARRAY3D_DEPTH_TEXTURE - This flag if set indicates that the CUDA array is a DEPTH_TEXTURE.
• CUDA_ARRAY3D_COLOR_ATTACHMENT - This flag indicates that the CUDA array may be bound as a color target in an external graphics API.
• CUDA_ARRAY3D_SPARSE - This flag if set indicates that the CUDA array or CUDA mipmapped array is a sparse CUDA array or CUDA mipmapped array respectively

See Also:

• Constant Field Values

CUDA_ARRAY3D_TEXTURE_GATHER

public static final int CUDA_ARRAY3D_TEXTURE_GATHER

Enum values:

• CUDA_ARRAY3D_LAYERED - If set, the CUDA array is a collection of layers, where each layer is either a 1D or a 2D array and the Depth member of CUDA_ARRAY3D_DESCRIPTOR specifies the number of layers, not the depth of a 3D array.
• CUDA_ARRAY3D_2DARRAY - Deprecated, use CUDA_ARRAY3D_LAYERED.
• CUDA_ARRAY3D_SURFACE_LDST - This flag must be set in order to bind a surface reference to the CUDA array.
• CUDA_ARRAY3D_CUBEMAP - If set, the CUDA array is a collection of six 2D arrays, representing faces of a cube. The width of such a CUDA array must be equal to its height, and Depth must be six. If CUDA_ARRAY3D_LAYERED flag is also set, then the CUDA array is a collection of cubemaps and Depth must be a multiple of six.
• CUDA_ARRAY3D_TEXTURE_GATHER - This flag must be set in order to perform texture gather operations on a CUDA array.
• CUDA_ARRAY3D_DEPTH_TEXTURE - This flag if set indicates that the CUDA array is a DEPTH_TEXTURE.
• CUDA_ARRAY3D_COLOR_ATTACHMENT - This flag indicates that the CUDA array may be bound as a color target in an external graphics API.
• CUDA_ARRAY3D_SPARSE - This flag if set indicates that the CUDA array or CUDA mipmapped array is a sparse CUDA array or CUDA mipmapped array respectively

See Also:

• Constant Field Values

CUDA_ARRAY3D_DEPTH_TEXTURE

public static final int CUDA_ARRAY3D_DEPTH_TEXTURE

Enum values:

• CUDA_ARRAY3D_LAYERED - If set, the CUDA array is a collection of layers, where each layer is either a 1D or a 2D array and the Depth member of CUDA_ARRAY3D_DESCRIPTOR specifies the number of layers, not the depth of a 3D array.
• CUDA_ARRAY3D_2DARRAY - Deprecated, use CUDA_ARRAY3D_LAYERED.
• CUDA_ARRAY3D_SURFACE_LDST - This flag must be set in order to bind a surface reference to the CUDA array.
• CUDA_ARRAY3D_CUBEMAP - If set, the CUDA array is a collection of six 2D arrays, representing faces of a cube. The width of such a CUDA array must be equal to its height, and Depth must be six. If CUDA_ARRAY3D_LAYERED flag is also set, then the CUDA array is a collection of cubemaps and Depth must be a multiple of six.
• CUDA_ARRAY3D_TEXTURE_GATHER - This flag must be set in order to perform texture gather operations on a CUDA array.
• CUDA_ARRAY3D_DEPTH_TEXTURE - This flag if set indicates that the CUDA array is a DEPTH_TEXTURE.
• CUDA_ARRAY3D_COLOR_ATTACHMENT - This flag indicates that the CUDA array may be bound as a color target in an external graphics API.
• CUDA_ARRAY3D_SPARSE - This flag if set indicates that the CUDA array or CUDA mipmapped array is a sparse CUDA array or CUDA mipmapped array respectively

See Also:

• Constant Field Values

CUDA_ARRAY3D_COLOR_ATTACHMENT

public static final int CUDA_ARRAY3D_COLOR_ATTACHMENT

Enum values:

• CUDA_ARRAY3D_LAYERED - If set, the CUDA array is a collection of layers, where each layer is either a 1D or a 2D array and the Depth member of CUDA_ARRAY3D_DESCRIPTOR specifies the number of layers, not the depth of a 3D array.
• CUDA_ARRAY3D_2DARRAY - Deprecated, use CUDA_ARRAY3D_LAYERED.
• CUDA_ARRAY3D_SURFACE_LDST - This flag must be set in order to bind a surface reference to the CUDA array.
• CUDA_ARRAY3D_CUBEMAP - If set, the CUDA array is a collection of six 2D arrays, representing faces of a cube. The width of such a CUDA array must be equal to its height, and Depth must be six. If CUDA_ARRAY3D_LAYERED flag is also set, then the CUDA array is a collection of cubemaps and Depth must be a multiple of six.
• CUDA_ARRAY3D_TEXTURE_GATHER - This flag must be set in order to perform texture gather operations on a CUDA array.
• CUDA_ARRAY3D_DEPTH_TEXTURE - This flag if set indicates that the CUDA array is a DEPTH_TEXTURE.
• CUDA_ARRAY3D_COLOR_ATTACHMENT - This flag indicates that the CUDA array may be bound as a color target in an external graphics API.
• CUDA_ARRAY3D_SPARSE - This flag if set indicates that the CUDA array or CUDA mipmapped array is a sparse CUDA array or CUDA mipmapped array respectively

See Also:

• Constant Field Values

CUDA_ARRAY3D_SPARSE

public static final int CUDA_ARRAY3D_SPARSE

Enum values:

• CUDA_ARRAY3D_LAYERED - If set, the CUDA array is a collection of layers, where each layer is either a 1D or a 2D array and the Depth member of CUDA_ARRAY3D_DESCRIPTOR specifies the number of layers, not the depth of a 3D array.
• CUDA_ARRAY3D_2DARRAY - Deprecated, use CUDA_ARRAY3D_LAYERED.
• CUDA_ARRAY3D_SURFACE_LDST - This flag must be set in order to bind a surface reference to the CUDA array.
• CUDA_ARRAY3D_CUBEMAP - If set, the CUDA array is a collection of six 2D arrays, representing faces of a cube. The width of such a CUDA array must be equal to its height, and Depth must be six. If CUDA_ARRAY3D_LAYERED flag is also set, then the CUDA array is a collection of cubemaps and Depth must be a multiple of six.
• CUDA_ARRAY3D_TEXTURE_GATHER - This flag must be set in order to perform texture gather operations on a CUDA array.
• CUDA_ARRAY3D_DEPTH_TEXTURE - This flag if set indicates that the CUDA array is a DEPTH_TEXTURE.
• CUDA_ARRAY3D_COLOR_ATTACHMENT - This flag indicates that the CUDA array may be bound as a color target in an external graphics API.
• CUDA_ARRAY3D_SPARSE - This flag if set indicates that the CUDA array or CUDA mipmapped array is a sparse CUDA array or CUDA mipmapped array respectively

See Also:

• Constant Field Values

CU_TRSA_OVERRIDE_FORMAT

public static final int CU_TRSA_OVERRIDE_FORMAT

Flag for TexRefSetArray.

Enum values:

• TRSA_OVERRIDE_FORMAT - Override the texref format with a format inferred from the array.

See Also:

• Constant Field Values

CU_TRSF_READ_AS_INTEGER

public static final int CU_TRSF_READ_AS_INTEGER

Flag for TexRefSetFlags.

Enum values:

• TRSF_READ_AS_INTEGER - Read the texture as integers rather than promoting the values to floats in the range [0,1].
• TRSF_NORMALIZED_COORDINATES - Use normalized texture coordinates in the range [0,1) instead of [0,dim).
• TRSF_SRGB - Perform sRGB->linear conversion during texture read.
• TRSF_DISABLE_TRILINEAR_OPTIMIZATION - Disable any trilinear filtering optimizations.

See Also:

• Constant Field Values

CU_TRSF_NORMALIZED_COORDINATES

public static final int CU_TRSF_NORMALIZED_COORDINATES

Flag for TexRefSetFlags.

Enum values:

• TRSF_READ_AS_INTEGER - Read the texture as integers rather than promoting the values to floats in the range [0,1].
• TRSF_NORMALIZED_COORDINATES - Use normalized texture coordinates in the range [0,1) instead of [0,dim).
• TRSF_SRGB - Perform sRGB->linear conversion during texture read.
• TRSF_DISABLE_TRILINEAR_OPTIMIZATION - Disable any trilinear filtering optimizations.

See Also:

• Constant Field Values

CU_TRSF_SRGB

public static final int CU_TRSF_SRGB

Flag for TexRefSetFlags.

Enum values:

• TRSF_READ_AS_INTEGER - Read the texture as integers rather than promoting the values to floats in the range [0,1].
• TRSF_NORMALIZED_COORDINATES - Use normalized texture coordinates in the range [0,1) instead of [0,dim).
• TRSF_SRGB - Perform sRGB->linear conversion during texture read.
• TRSF_DISABLE_TRILINEAR_OPTIMIZATION - Disable any trilinear filtering optimizations.

See Also:

• Constant Field Values

CU_TRSF_DISABLE_TRILINEAR_OPTIMIZATION

public static final int CU_TRSF_DISABLE_TRILINEAR_OPTIMIZATION

Flag for TexRefSetFlags.

Enum values:

• TRSF_READ_AS_INTEGER - Read the texture as integers rather than promoting the values to floats in the range [0,1].
• TRSF_NORMALIZED_COORDINATES - Use normalized texture coordinates in the range [0,1) instead of [0,dim).
• TRSF_SRGB - Perform sRGB->linear conversion during texture read.
• TRSF_DISABLE_TRILINEAR_OPTIMIZATION - Disable any trilinear filtering optimizations.

See Also:

• Constant Field Values

CU_LAUNCH_PARAM_END

public static final long CU_LAUNCH_PARAM_END

End of array terminator for the extra parameter to LaunchKernel.

See Also:

• Constant Field Values

CU_LAUNCH_PARAM_BUFFER_POINTER

public static final long CU_LAUNCH_PARAM_BUFFER_POINTER

Indicator that the next value in the extra parameter to LaunchKernel will be a pointer to a buffer containing all kernel parameters used for launching kernel f.

This buffer needs to honor all alignment/padding requirements of the individual parameters. If LAUNCH_PARAM_BUFFER_SIZE is not also specified in the extra array, then LAUNCH_PARAM_BUFFER_POINTER will have no effect.

See Also:

• Constant Field Values

CU_LAUNCH_PARAM_BUFFER_SIZE

public static final long CU_LAUNCH_PARAM_BUFFER_SIZE

Indicator that the next value in the extra parameter to LaunchKernel will be a pointer to a size_t which contains the size of the buffer specified with LAUNCH_PARAM_BUFFER_POINTER.

It is required that CU_LAUNCH_PARAM_BUFFER_POINTER also be specified in the extra array if the value associated with CU_LAUNCH_PARAM_BUFFER_SIZE is not zero.

See Also:

• Constant Field Values

CU_PARAM_TR_DEFAULT

public static final int CU_PARAM_TR_DEFAULT

For texture references loaded into the module, use default texunit from texture reference.

See Also:

• Constant Field Values

CU_DEVICE_CPU

public static final int CU_DEVICE_CPU

Device that represents the CPU.

See Also:

• Constant Field Values

CU_DEVICE_INVALID

public static final int CU_DEVICE_INVALID

Device that represents an invalid device.

See Also:

• Constant Field Values

CU_FLUSH_GPU_DIRECT_RDMA_WRITES_OPTION_HOST

public static final int CU_FLUSH_GPU_DIRECT_RDMA_WRITES_OPTION_HOST

Bitmasks for DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS. (CUflushGPUDirectRDMAWritesOptions)

Enum values:

• FLUSH_GPU_DIRECT_RDMA_WRITES_OPTION_HOST - FlushGPUDirectRDMAWrites and its CUDA Runtime API counterpart are supported on the device.
• FLUSH_GPU_DIRECT_RDMA_WRITES_OPTION_MEMOPS - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device.

See Also:

• Constant Field Values

CU_FLUSH_GPU_DIRECT_RDMA_WRITES_OPTION_MEMOPS

public static final int CU_FLUSH_GPU_DIRECT_RDMA_WRITES_OPTION_MEMOPS

Bitmasks for DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS. (CUflushGPUDirectRDMAWritesOptions)

Enum values:

• FLUSH_GPU_DIRECT_RDMA_WRITES_OPTION_HOST - FlushGPUDirectRDMAWrites and its CUDA Runtime API counterpart are supported on the device.
• FLUSH_GPU_DIRECT_RDMA_WRITES_OPTION_MEMOPS - The STREAM_WAIT_VALUE_FLUSH flag and the STREAM_MEM_OP_FLUSH_REMOTE_WRITES MemOp are supported on the device.

See Also:

• Constant Field Values

CU_GPU_DIRECT_RDMA_WRITES_ORDERING_NONE

public static final int CU_GPU_DIRECT_RDMA_WRITES_ORDERING_NONE

Platform native ordering for GPUDirect RDMA writes. (CUGPUDirectRDMAWritesOrdering)

Enum values:

• GPU_DIRECT_RDMA_WRITES_ORDERING_NONE - The device does not natively support ordering of remote writes. FlushGPUDirectRDMAWrites can be leveraged if supported.
• GPU_DIRECT_RDMA_WRITES_ORDERING_OWNER - Natively, the device can consistently consume remote writes, although other CUDA devices may not.
• GPU_DIRECT_RDMA_WRITES_ORDERING_ALL_DEVICES - Any CUDA device in the system can consistently consume remote writes to this device.

See Also:

• Constant Field Values

CU_GPU_DIRECT_RDMA_WRITES_ORDERING_OWNER

public static final int CU_GPU_DIRECT_RDMA_WRITES_ORDERING_OWNER

Platform native ordering for GPUDirect RDMA writes. (CUGPUDirectRDMAWritesOrdering)

Enum values:

• GPU_DIRECT_RDMA_WRITES_ORDERING_NONE - The device does not natively support ordering of remote writes. FlushGPUDirectRDMAWrites can be leveraged if supported.
• GPU_DIRECT_RDMA_WRITES_ORDERING_OWNER - Natively, the device can consistently consume remote writes, although other CUDA devices may not.
• GPU_DIRECT_RDMA_WRITES_ORDERING_ALL_DEVICES - Any CUDA device in the system can consistently consume remote writes to this device.

See Also:

• Constant Field Values

CU_GPU_DIRECT_RDMA_WRITES_ORDERING_ALL_DEVICES

public static final int CU_GPU_DIRECT_RDMA_WRITES_ORDERING_ALL_DEVICES

Platform native ordering for GPUDirect RDMA writes. (CUGPUDirectRDMAWritesOrdering)

Enum values:

• GPU_DIRECT_RDMA_WRITES_ORDERING_NONE - The device does not natively support ordering of remote writes. FlushGPUDirectRDMAWrites can be leveraged if supported.
• GPU_DIRECT_RDMA_WRITES_ORDERING_OWNER - Natively, the device can consistently consume remote writes, although other CUDA devices may not.
• GPU_DIRECT_RDMA_WRITES_ORDERING_ALL_DEVICES - Any CUDA device in the system can consistently consume remote writes to this device.

See Also:

• Constant Field Values

CU_FLUSH_GPU_DIRECT_RDMA_WRITES_TO_OWNER

public static final int CU_FLUSH_GPU_DIRECT_RDMA_WRITES_TO_OWNER

The scopes for FlushGPUDirectRDMAWrites (CUflushGPUDirectRDMAWritesScope)

Enum values:

• FLUSH_GPU_DIRECT_RDMA_WRITES_TO_OWNER - Blocks until remote writes are visible to the CUDA device context owning the data.
• FLUSH_GPU_DIRECT_RDMA_WRITES_TO_ALL_DEVICES - Blocks until remote writes are visible to all CUDA device contexts.

See Also:

• Constant Field Values

CU_FLUSH_GPU_DIRECT_RDMA_WRITES_TO_ALL_DEVICES

public static final int CU_FLUSH_GPU_DIRECT_RDMA_WRITES_TO_ALL_DEVICES

The scopes for FlushGPUDirectRDMAWrites (CUflushGPUDirectRDMAWritesScope)

Enum values:

• FLUSH_GPU_DIRECT_RDMA_WRITES_TO_OWNER - Blocks until remote writes are visible to the CUDA device context owning the data.
• FLUSH_GPU_DIRECT_RDMA_WRITES_TO_ALL_DEVICES - Blocks until remote writes are visible to all CUDA device contexts.

See Also:

• Constant Field Values

CU_FLUSH_GPU_DIRECT_RDMA_WRITES_TARGET_CURRENT_CTX

public static final int CU_FLUSH_GPU_DIRECT_RDMA_WRITES_TARGET_CURRENT_CTX

The targets for FlushGPUDirectRDMAWrites (CUflushGPUDirectRDMAWritesTarget)

Enum values:

• FLUSH_GPU_DIRECT_RDMA_WRITES_TARGET_CURRENT_CTX - Sets the target for cuFlushGPUDirectRDMAWrites() to the currently active CUDA device context.

See Also:

• Constant Field Values

CU_GRAPH_DEBUG_DOT_FLAGS_VERBOSE

public static final int CU_GRAPH_DEBUG_DOT_FLAGS_VERBOSE

The additional write options for GraphDebugDotPrint (CUgraphDebugDot_flags)

Enum values:

• GRAPH_DEBUG_DOT_FLAGS_VERBOSE
• GRAPH_DEBUG_DOT_FLAGS_RUNTIME_TYPES - Output all debug data as if every debug flag is enabled
• GRAPH_DEBUG_DOT_FLAGS_KERNEL_NODE_PARAMS - Use CUDA Runtime structures for output
• GRAPH_DEBUG_DOT_FLAGS_MEMCPY_NODE_PARAMS - Adds CUDA_KERNEL_NODE_PARAMS values to output
• GRAPH_DEBUG_DOT_FLAGS_MEMSET_NODE_PARAMS - Adds CUDA_MEMCPY3D values to output
• GRAPH_DEBUG_DOT_FLAGS_HOST_NODE_PARAMS - Adds CUDA_MEMSET_NODE_PARAMS values to output
• GRAPH_DEBUG_DOT_FLAGS_EVENT_NODE_PARAMS - Adds CUDA_HOST_NODE_PARAMS values to output
• GRAPH_DEBUG_DOT_FLAGS_EXT_SEMAS_SIGNAL_NODE_PARAMS - Adds CUevent handle from record and wait nodes to output
• GRAPH_DEBUG_DOT_FLAGS_EXT_SEMAS_WAIT_NODE_PARAMS - Adds CUDA_EXT_SEM_SIGNAL_NODE_PARAMS values to output
• GRAPH_DEBUG_DOT_FLAGS_KERNEL_NODE_ATTRIBUTES - Adds CUDA_EXT_SEM_WAIT_NODE_PARAMS values to output
• GRAPH_DEBUG_DOT_FLAGS_HANDLES - Adds CUkernelNodeAttrValue values to output
• GRAPH_DEBUG_DOT_FLAGS_MEM_ALLOC_NODE_PARAMS - Adds node handles and every kernel function handle to output
• GRAPH_DEBUG_DOT_FLAGS_MEM_FREE_NODE_PARAMS - Adds memory alloc node parameters to output

See Also:

• Constant Field Values

CU_GRAPH_DEBUG_DOT_FLAGS_RUNTIME_TYPES

public static final int CU_GRAPH_DEBUG_DOT_FLAGS_RUNTIME_TYPES

The additional write options for GraphDebugDotPrint (CUgraphDebugDot_flags)

Enum values:

• GRAPH_DEBUG_DOT_FLAGS_VERBOSE
• GRAPH_DEBUG_DOT_FLAGS_RUNTIME_TYPES - Output all debug data as if every debug flag is enabled
• GRAPH_DEBUG_DOT_FLAGS_KERNEL_NODE_PARAMS - Use CUDA Runtime structures for output
• GRAPH_DEBUG_DOT_FLAGS_MEMCPY_NODE_PARAMS - Adds CUDA_KERNEL_NODE_PARAMS values to output
• GRAPH_DEBUG_DOT_FLAGS_MEMSET_NODE_PARAMS - Adds CUDA_MEMCPY3D values to output
• GRAPH_DEBUG_DOT_FLAGS_HOST_NODE_PARAMS - Adds CUDA_MEMSET_NODE_PARAMS values to output
• GRAPH_DEBUG_DOT_FLAGS_EVENT_NODE_PARAMS - Adds CUDA_HOST_NODE_PARAMS values to output
• GRAPH_DEBUG_DOT_FLAGS_EXT_SEMAS_SIGNAL_NODE_PARAMS - Adds CUevent handle from record and wait nodes to output
• GRAPH_DEBUG_DOT_FLAGS_EXT_SEMAS_WAIT_NODE_PARAMS - Adds CUDA_EXT_SEM_SIGNAL_NODE_PARAMS values to output
• GRAPH_DEBUG_DOT_FLAGS_KERNEL_NODE_ATTRIBUTES - Adds CUDA_EXT_SEM_WAIT_NODE_PARAMS values to output
• GRAPH_DEBUG_DOT_FLAGS_HANDLES - Adds CUkernelNodeAttrValue values to output
• GRAPH_DEBUG_DOT_FLAGS_MEM_ALLOC_NODE_PARAMS - Adds node handles and every kernel function handle to output
• GRAPH_DEBUG_DOT_FLAGS_MEM_FREE_NODE_PARAMS - Adds memory alloc node parameters to output

See Also:

• Constant Field Values

CU_GRAPH_DEBUG_DOT_FLAGS_KERNEL_NODE_PARAMS

public static final int CU_GRAPH_DEBUG_DOT_FLAGS_KERNEL_NODE_PARAMS

The additional write options for GraphDebugDotPrint (CUgraphDebugDot_flags)

Enum values:

• GRAPH_DEBUG_DOT_FLAGS_VERBOSE
• GRAPH_DEBUG_DOT_FLAGS_RUNTIME_TYPES - Output all debug data as if every debug flag is enabled
• GRAPH_DEBUG_DOT_FLAGS_KERNEL_NODE_PARAMS - Use CUDA Runtime structures for output
• GRAPH_DEBUG_DOT_FLAGS_MEMCPY_NODE_PARAMS - Adds CUDA_KERNEL_NODE_PARAMS values to output
• GRAPH_DEBUG_DOT_FLAGS_MEMSET_NODE_PARAMS - Adds CUDA_MEMCPY3D values to output
• GRAPH_DEBUG_DOT_FLAGS_HOST_NODE_PARAMS - Adds CUDA_MEMSET_NODE_PARAMS values to output
• GRAPH_DEBUG_DOT_FLAGS_EVENT_NODE_PARAMS - Adds CUDA_HOST_NODE_PARAMS values to output
• GRAPH_DEBUG_DOT_FLAGS_EXT_SEMAS_SIGNAL_NODE_PARAMS - Adds CUevent handle from record and wait nodes to output
• GRAPH_DEBUG_DOT_FLAGS_EXT_SEMAS_WAIT_NODE_PARAMS - Adds CUDA_EXT_SEM_SIGNAL_NODE_PARAMS values to output
• GRAPH_DEBUG_DOT_FLAGS_KERNEL_NODE_ATTRIBUTES - Adds CUDA_EXT_SEM_WAIT_NODE_PARAMS values to output
• GRAPH_DEBUG_DOT_FLAGS_HANDLES - Adds CUkernelNodeAttrValue values to output
• GRAPH_DEBUG_DOT_FLAGS_MEM_ALLOC_NODE_PARAMS - Adds node handles and every kernel function handle to output
• GRAPH_DEBUG_DOT_FLAGS_MEM_FREE_NODE_PARAMS - Adds memory alloc node parameters to output

See Also:

• Constant Field Values

CU_GRAPH_DEBUG_DOT_FLAGS_MEMCPY_NODE_PARAMS

public static final int CU_GRAPH_DEBUG_DOT_FLAGS_MEMCPY_NODE_PARAMS

The additional write options for GraphDebugDotPrint (CUgraphDebugDot_flags)

Enum values:

• GRAPH_DEBUG_DOT_FLAGS_VERBOSE
• GRAPH_DEBUG_DOT_FLAGS_RUNTIME_TYPES - Output all debug data as if every debug flag is enabled
• GRAPH_DEBUG_DOT_FLAGS_KERNEL_NODE_PARAMS - Use CUDA Runtime structures for output
• GRAPH_DEBUG_DOT_FLAGS_MEMCPY_NODE_PARAMS - Adds CUDA_KERNEL_NODE_PARAMS values to output
• GRAPH_DEBUG_DOT_FLAGS_MEMSET_NODE_PARAMS - Adds CUDA_MEMCPY3D values to output
• GRAPH_DEBUG_DOT_FLAGS_HOST_NODE_PARAMS - Adds CUDA_MEMSET_NODE_PARAMS values to output
• GRAPH_DEBUG_DOT_FLAGS_EVENT_NODE_PARAMS - Adds CUDA_HOST_NODE_PARAMS values to output
• GRAPH_DEBUG_DOT_FLAGS_EXT_SEMAS_SIGNAL_NODE_PARAMS - Adds CUevent handle from record and wait nodes to output
• GRAPH_DEBUG_DOT_FLAGS_EXT_SEMAS_WAIT_NODE_PARAMS - Adds CUDA_EXT_SEM_SIGNAL_NODE_PARAMS values to output
• GRAPH_DEBUG_DOT_FLAGS_KERNEL_NODE_ATTRIBUTES - Adds CUDA_EXT_SEM_WAIT_NODE_PARAMS values to output
• GRAPH_DEBUG_DOT_FLAGS_HANDLES - Adds CUkernelNodeAttrValue values to output
• GRAPH_DEBUG_DOT_FLAGS_MEM_ALLOC_NODE_PARAMS - Adds node handles and every kernel function handle to output
• GRAPH_DEBUG_DOT_FLAGS_MEM_FREE_NODE_PARAMS - Adds memory alloc node parameters to output

See Also:

• Constant Field Values

CU_GRAPH_DEBUG_DOT_FLAGS_MEMSET_NODE_PARAMS

public static final int CU_GRAPH_DEBUG_DOT_FLAGS_MEMSET_NODE_PARAMS

The additional write options for GraphDebugDotPrint (CUgraphDebugDot_flags)

Enum values:

• GRAPH_DEBUG_DOT_FLAGS_VERBOSE
• GRAPH_DEBUG_DOT_FLAGS_RUNTIME_TYPES - Output all debug data as if every debug flag is enabled
• GRAPH_DEBUG_DOT_FLAGS_KERNEL_NODE_PARAMS - Use CUDA Runtime structures for output
• GRAPH_DEBUG_DOT_FLAGS_MEMCPY_NODE_PARAMS - Adds CUDA_KERNEL_NODE_PARAMS values to output
• GRAPH_DEBUG_DOT_FLAGS_MEMSET_NODE_PARAMS - Adds CUDA_MEMCPY3D values to output
• GRAPH_DEBUG_DOT_FLAGS_HOST_NODE_PARAMS - Adds CUDA_MEMSET_NODE_PARAMS values to output
• GRAPH_DEBUG_DOT_FLAGS_EVENT_NODE_PARAMS - Adds CUDA_HOST_NODE_PARAMS values to output
• GRAPH_DEBUG_DOT_FLAGS_EXT_SEMAS_SIGNAL_NODE_PARAMS - Adds CUevent handle from record and wait nodes to output
• GRAPH_DEBUG_DOT_FLAGS_EXT_SEMAS_WAIT_NODE_PARAMS - Adds CUDA_EXT_SEM_SIGNAL_NODE_PARAMS values to output
• GRAPH_DEBUG_DOT_FLAGS_KERNEL_NODE_ATTRIBUTES - Adds CUDA_EXT_SEM_WAIT_NODE_PARAMS values to output
• GRAPH_DEBUG_DOT_FLAGS_HANDLES - Adds CUkernelNodeAttrValue values to output
• GRAPH_DEBUG_DOT_FLAGS_MEM_ALLOC_NODE_PARAMS - Adds node handles and every kernel function handle to output
• GRAPH_DEBUG_DOT_FLAGS_MEM_FREE_NODE_PARAMS - Adds memory alloc node parameters to output

See Also:

• Constant Field Values

CU_GRAPH_DEBUG_DOT_FLAGS_HOST_NODE_PARAMS

public static final int CU_GRAPH_DEBUG_DOT_FLAGS_HOST_NODE_PARAMS

The additional write options for GraphDebugDotPrint (CUgraphDebugDot_flags)

Enum values:

• GRAPH_DEBUG_DOT_FLAGS_VERBOSE
• GRAPH_DEBUG_DOT_FLAGS_RUNTIME_TYPES - Output all debug data as if every debug flag is enabled
• GRAPH_DEBUG_DOT_FLAGS_KERNEL_NODE_PARAMS - Use CUDA Runtime structures for output
• GRAPH_DEBUG_DOT_FLAGS_MEMCPY_NODE_PARAMS - Adds CUDA_KERNEL_NODE_PARAMS values to output
• GRAPH_DEBUG_DOT_FLAGS_MEMSET_NODE_PARAMS - Adds CUDA_MEMCPY3D values to output
• GRAPH_DEBUG_DOT_FLAGS_HOST_NODE_PARAMS - Adds CUDA_MEMSET_NODE_PARAMS values to output
• GRAPH_DEBUG_DOT_FLAGS_EVENT_NODE_PARAMS - Adds CUDA_HOST_NODE_PARAMS values to output
• GRAPH_DEBUG_DOT_FLAGS_EXT_SEMAS_SIGNAL_NODE_PARAMS - Adds CUevent handle from record and wait nodes to output
• GRAPH_DEBUG_DOT_FLAGS_EXT_SEMAS_WAIT_NODE_PARAMS - Adds CUDA_EXT_SEM_SIGNAL_NODE_PARAMS values to output
• GRAPH_DEBUG_DOT_FLAGS_KERNEL_NODE_ATTRIBUTES - Adds CUDA_EXT_SEM_WAIT_NODE_PARAMS values to output
• GRAPH_DEBUG_DOT_FLAGS_HANDLES - Adds CUkernelNodeAttrValue values to output
• GRAPH_DEBUG_DOT_FLAGS_MEM_ALLOC_NODE_PARAMS - Adds node handles and every kernel function handle to output
• GRAPH_DEBUG_DOT_FLAGS_MEM_FREE_NODE_PARAMS - Adds memory alloc node parameters to output

See Also:

• Constant Field Values

CU_GRAPH_DEBUG_DOT_FLAGS_EVENT_NODE_PARAMS

public static final int CU_GRAPH_DEBUG_DOT_FLAGS_EVENT_NODE_PARAMS

The additional write options for GraphDebugDotPrint (CUgraphDebugDot_flags)

Enum values:

• GRAPH_DEBUG_DOT_FLAGS_VERBOSE
• GRAPH_DEBUG_DOT_FLAGS_RUNTIME_TYPES - Output all debug data as if every debug flag is enabled
• GRAPH_DEBUG_DOT_FLAGS_KERNEL_NODE_PARAMS - Use CUDA Runtime structures for output
• GRAPH_DEBUG_DOT_FLAGS_MEMCPY_NODE_PARAMS - Adds CUDA_KERNEL_NODE_PARAMS values to output
• GRAPH_DEBUG_DOT_FLAGS_MEMSET_NODE_PARAMS - Adds CUDA_MEMCPY3D values to output
• GRAPH_DEBUG_DOT_FLAGS_HOST_NODE_PARAMS - Adds CUDA_MEMSET_NODE_PARAMS values to output
• GRAPH_DEBUG_DOT_FLAGS_EVENT_NODE_PARAMS - Adds CUDA_HOST_NODE_PARAMS values to output
• GRAPH_DEBUG_DOT_FLAGS_EXT_SEMAS_SIGNAL_NODE_PARAMS - Adds CUevent handle from record and wait nodes to output
• GRAPH_DEBUG_DOT_FLAGS_EXT_SEMAS_WAIT_NODE_PARAMS - Adds CUDA_EXT_SEM_SIGNAL_NODE_PARAMS values to output
• GRAPH_DEBUG_DOT_FLAGS_KERNEL_NODE_ATTRIBUTES - Adds CUDA_EXT_SEM_WAIT_NODE_PARAMS values to output
• GRAPH_DEBUG_DOT_FLAGS_HANDLES - Adds CUkernelNodeAttrValue values to output
• GRAPH_DEBUG_DOT_FLAGS_MEM_ALLOC_NODE_PARAMS - Adds node handles and every kernel function handle to output
• GRAPH_DEBUG_DOT_FLAGS_MEM_FREE_NODE_PARAMS - Adds memory alloc node parameters to output

See Also:

• Constant Field Values

CU_GRAPH_DEBUG_DOT_FLAGS_EXT_SEMAS_SIGNAL_NODE_PARAMS

public static final int CU_GRAPH_DEBUG_DOT_FLAGS_EXT_SEMAS_SIGNAL_NODE_PARAMS

The additional write options for GraphDebugDotPrint (CUgraphDebugDot_flags)

Enum values:

• GRAPH_DEBUG_DOT_FLAGS_VERBOSE
• GRAPH_DEBUG_DOT_FLAGS_RUNTIME_TYPES - Output all debug data as if every debug flag is enabled
• GRAPH_DEBUG_DOT_FLAGS_KERNEL_NODE_PARAMS - Use CUDA Runtime structures for output
• GRAPH_DEBUG_DOT_FLAGS_MEMCPY_NODE_PARAMS - Adds CUDA_KERNEL_NODE_PARAMS values to output
• GRAPH_DEBUG_DOT_FLAGS_MEMSET_NODE_PARAMS - Adds CUDA_MEMCPY3D values to output
• GRAPH_DEBUG_DOT_FLAGS_HOST_NODE_PARAMS - Adds CUDA_MEMSET_NODE_PARAMS values to output
• GRAPH_DEBUG_DOT_FLAGS_EVENT_NODE_PARAMS - Adds CUDA_HOST_NODE_PARAMS values to output
• GRAPH_DEBUG_DOT_FLAGS_EXT_SEMAS_SIGNAL_NODE_PARAMS - Adds CUevent handle from record and wait nodes to output
• GRAPH_DEBUG_DOT_FLAGS_EXT_SEMAS_WAIT_NODE_PARAMS - Adds CUDA_EXT_SEM_SIGNAL_NODE_PARAMS values to output
• GRAPH_DEBUG_DOT_FLAGS_KERNEL_NODE_ATTRIBUTES - Adds CUDA_EXT_SEM_WAIT_NODE_PARAMS values to output
• GRAPH_DEBUG_DOT_FLAGS_HANDLES - Adds CUkernelNodeAttrValue values to output
• GRAPH_DEBUG_DOT_FLAGS_MEM_ALLOC_NODE_PARAMS - Adds node handles and every kernel function handle to output
• GRAPH_DEBUG_DOT_FLAGS_MEM_FREE_NODE_PARAMS - Adds memory alloc node parameters to output

See Also:

• Constant Field Values

CU_GRAPH_DEBUG_DOT_FLAGS_EXT_SEMAS_WAIT_NODE_PARAMS

public static final int CU_GRAPH_DEBUG_DOT_FLAGS_EXT_SEMAS_WAIT_NODE_PARAMS

The additional write options for GraphDebugDotPrint (CUgraphDebugDot_flags)

Enum values:

• GRAPH_DEBUG_DOT_FLAGS_VERBOSE
• GRAPH_DEBUG_DOT_FLAGS_RUNTIME_TYPES - Output all debug data as if every debug flag is enabled
• GRAPH_DEBUG_DOT_FLAGS_KERNEL_NODE_PARAMS - Use CUDA Runtime structures for output
• GRAPH_DEBUG_DOT_FLAGS_MEMCPY_NODE_PARAMS - Adds CUDA_KERNEL_NODE_PARAMS values to output
• GRAPH_DEBUG_DOT_FLAGS_MEMSET_NODE_PARAMS - Adds CUDA_MEMCPY3D values to output
• GRAPH_DEBUG_DOT_FLAGS_HOST_NODE_PARAMS - Adds CUDA_MEMSET_NODE_PARAMS values to output
• GRAPH_DEBUG_DOT_FLAGS_EVENT_NODE_PARAMS - Adds CUDA_HOST_NODE_PARAMS values to output
• GRAPH_DEBUG_DOT_FLAGS_EXT_SEMAS_SIGNAL_NODE_PARAMS - Adds CUevent handle from record and wait nodes to output
• GRAPH_DEBUG_DOT_FLAGS_EXT_SEMAS_WAIT_NODE_PARAMS - Adds CUDA_EXT_SEM_SIGNAL_NODE_PARAMS values to output
• GRAPH_DEBUG_DOT_FLAGS_KERNEL_NODE_ATTRIBUTES - Adds CUDA_EXT_SEM_WAIT_NODE_PARAMS values to output
• GRAPH_DEBUG_DOT_FLAGS_HANDLES - Adds CUkernelNodeAttrValue values to output
• GRAPH_DEBUG_DOT_FLAGS_MEM_ALLOC_NODE_PARAMS - Adds node handles and every kernel function handle to output
• GRAPH_DEBUG_DOT_FLAGS_MEM_FREE_NODE_PARAMS - Adds memory alloc node parameters to output

See Also:

• Constant Field Values

CU_GRAPH_DEBUG_DOT_FLAGS_KERNEL_NODE_ATTRIBUTES

public static final int CU_GRAPH_DEBUG_DOT_FLAGS_KERNEL_NODE_ATTRIBUTES

The additional write options for GraphDebugDotPrint (CUgraphDebugDot_flags)

Enum values:

• GRAPH_DEBUG_DOT_FLAGS_VERBOSE
• GRAPH_DEBUG_DOT_FLAGS_RUNTIME_TYPES - Output all debug data as if every debug flag is enabled
• GRAPH_DEBUG_DOT_FLAGS_KERNEL_NODE_PARAMS - Use CUDA Runtime structures for output
• GRAPH_DEBUG_DOT_FLAGS_MEMCPY_NODE_PARAMS - Adds CUDA_KERNEL_NODE_PARAMS values to output
• GRAPH_DEBUG_DOT_FLAGS_MEMSET_NODE_PARAMS - Adds CUDA_MEMCPY3D values to output
• GRAPH_DEBUG_DOT_FLAGS_HOST_NODE_PARAMS - Adds CUDA_MEMSET_NODE_PARAMS values to output
• GRAPH_DEBUG_DOT_FLAGS_EVENT_NODE_PARAMS - Adds CUDA_HOST_NODE_PARAMS values to output
• GRAPH_DEBUG_DOT_FLAGS_EXT_SEMAS_SIGNAL_NODE_PARAMS - Adds CUevent handle from record and wait nodes to output
• GRAPH_DEBUG_DOT_FLAGS_EXT_SEMAS_WAIT_NODE_PARAMS - Adds CUDA_EXT_SEM_SIGNAL_NODE_PARAMS values to output
• GRAPH_DEBUG_DOT_FLAGS_KERNEL_NODE_ATTRIBUTES - Adds CUDA_EXT_SEM_WAIT_NODE_PARAMS values to output
• GRAPH_DEBUG_DOT_FLAGS_HANDLES - Adds CUkernelNodeAttrValue values to output
• GRAPH_DEBUG_DOT_FLAGS_MEM_ALLOC_NODE_PARAMS - Adds node handles and every kernel function handle to output
• GRAPH_DEBUG_DOT_FLAGS_MEM_FREE_NODE_PARAMS - Adds memory alloc node parameters to output

See Also:

• Constant Field Values

CU_GRAPH_DEBUG_DOT_FLAGS_HANDLES

public static final int CU_GRAPH_DEBUG_DOT_FLAGS_HANDLES

The additional write options for GraphDebugDotPrint (CUgraphDebugDot_flags)

Enum values:

• GRAPH_DEBUG_DOT_FLAGS_VERBOSE
• GRAPH_DEBUG_DOT_FLAGS_RUNTIME_TYPES - Output all debug data as if every debug flag is enabled
• GRAPH_DEBUG_DOT_FLAGS_KERNEL_NODE_PARAMS - Use CUDA Runtime structures for output
• GRAPH_DEBUG_DOT_FLAGS_MEMCPY_NODE_PARAMS - Adds CUDA_KERNEL_NODE_PARAMS values to output
• GRAPH_DEBUG_DOT_FLAGS_MEMSET_NODE_PARAMS - Adds CUDA_MEMCPY3D values to output
• GRAPH_DEBUG_DOT_FLAGS_HOST_NODE_PARAMS - Adds CUDA_MEMSET_NODE_PARAMS values to output
• GRAPH_DEBUG_DOT_FLAGS_EVENT_NODE_PARAMS - Adds CUDA_HOST_NODE_PARAMS values to output
• GRAPH_DEBUG_DOT_FLAGS_EXT_SEMAS_SIGNAL_NODE_PARAMS - Adds CUevent handle from record and wait nodes to output
• GRAPH_DEBUG_DOT_FLAGS_EXT_SEMAS_WAIT_NODE_PARAMS - Adds CUDA_EXT_SEM_SIGNAL_NODE_PARAMS values to output
• GRAPH_DEBUG_DOT_FLAGS_KERNEL_NODE_ATTRIBUTES - Adds CUDA_EXT_SEM_WAIT_NODE_PARAMS values to output
• GRAPH_DEBUG_DOT_FLAGS_HANDLES - Adds CUkernelNodeAttrValue values to output
• GRAPH_DEBUG_DOT_FLAGS_MEM_ALLOC_NODE_PARAMS - Adds node handles and every kernel function handle to output
• GRAPH_DEBUG_DOT_FLAGS_MEM_FREE_NODE_PARAMS - Adds memory alloc node parameters to output

See Also:

• Constant Field Values

CU_GRAPH_DEBUG_DOT_FLAGS_MEM_ALLOC_NODE_PARAMS

public static final int CU_GRAPH_DEBUG_DOT_FLAGS_MEM_ALLOC_NODE_PARAMS

The additional write options for GraphDebugDotPrint (CUgraphDebugDot_flags)

Enum values:

• GRAPH_DEBUG_DOT_FLAGS_VERBOSE
• GRAPH_DEBUG_DOT_FLAGS_RUNTIME_TYPES - Output all debug data as if every debug flag is enabled
• GRAPH_DEBUG_DOT_FLAGS_KERNEL_NODE_PARAMS - Use CUDA Runtime structures for output
• GRAPH_DEBUG_DOT_FLAGS_MEMCPY_NODE_PARAMS - Adds CUDA_KERNEL_NODE_PARAMS values to output
• GRAPH_DEBUG_DOT_FLAGS_MEMSET_NODE_PARAMS - Adds CUDA_MEMCPY3D values to output
• GRAPH_DEBUG_DOT_FLAGS_HOST_NODE_PARAMS - Adds CUDA_MEMSET_NODE_PARAMS values to output
• GRAPH_DEBUG_DOT_FLAGS_EVENT_NODE_PARAMS - Adds CUDA_HOST_NODE_PARAMS values to output
• GRAPH_DEBUG_DOT_FLAGS_EXT_SEMAS_SIGNAL_NODE_PARAMS - Adds CUevent handle from record and wait nodes to output
• GRAPH_DEBUG_DOT_FLAGS_EXT_SEMAS_WAIT_NODE_PARAMS - Adds CUDA_EXT_SEM_SIGNAL_NODE_PARAMS values to output
• GRAPH_DEBUG_DOT_FLAGS_KERNEL_NODE_ATTRIBUTES - Adds CUDA_EXT_SEM_WAIT_NODE_PARAMS values to output
• GRAPH_DEBUG_DOT_FLAGS_HANDLES - Adds CUkernelNodeAttrValue values to output
• GRAPH_DEBUG_DOT_FLAGS_MEM_ALLOC_NODE_PARAMS - Adds node handles and every kernel function handle to output
• GRAPH_DEBUG_DOT_FLAGS_MEM_FREE_NODE_PARAMS - Adds memory alloc node parameters to output

See Also:

• Constant Field Values

CU_GRAPH_DEBUG_DOT_FLAGS_MEM_FREE_NODE_PARAMS

public static final int CU_GRAPH_DEBUG_DOT_FLAGS_MEM_FREE_NODE_PARAMS

The additional write options for GraphDebugDotPrint (CUgraphDebugDot_flags)

Enum values:

• GRAPH_DEBUG_DOT_FLAGS_VERBOSE
• GRAPH_DEBUG_DOT_FLAGS_RUNTIME_TYPES - Output all debug data as if every debug flag is enabled
• GRAPH_DEBUG_DOT_FLAGS_KERNEL_NODE_PARAMS - Use CUDA Runtime structures for output
• GRAPH_DEBUG_DOT_FLAGS_MEMCPY_NODE_PARAMS - Adds CUDA_KERNEL_NODE_PARAMS values to output
• GRAPH_DEBUG_DOT_FLAGS_MEMSET_NODE_PARAMS - Adds CUDA_MEMCPY3D values to output
• GRAPH_DEBUG_DOT_FLAGS_HOST_NODE_PARAMS - Adds CUDA_MEMSET_NODE_PARAMS values to output
• GRAPH_DEBUG_DOT_FLAGS_EVENT_NODE_PARAMS - Adds CUDA_HOST_NODE_PARAMS values to output
• GRAPH_DEBUG_DOT_FLAGS_EXT_SEMAS_SIGNAL_NODE_PARAMS - Adds CUevent handle from record and wait nodes to output
• GRAPH_DEBUG_DOT_FLAGS_EXT_SEMAS_WAIT_NODE_PARAMS - Adds CUDA_EXT_SEM_SIGNAL_NODE_PARAMS values to output
• GRAPH_DEBUG_DOT_FLAGS_KERNEL_NODE_ATTRIBUTES - Adds CUDA_EXT_SEM_WAIT_NODE_PARAMS values to output
• GRAPH_DEBUG_DOT_FLAGS_HANDLES - Adds CUkernelNodeAttrValue values to output
• GRAPH_DEBUG_DOT_FLAGS_MEM_ALLOC_NODE_PARAMS - Adds node handles and every kernel function handle to output
• GRAPH_DEBUG_DOT_FLAGS_MEM_FREE_NODE_PARAMS - Adds memory alloc node parameters to output

See Also:

• Constant Field Values

CU_USER_OBJECT_NO_DESTRUCTOR_SYNC

public static final int CU_USER_OBJECT_NO_DESTRUCTOR_SYNC

Flags for user objects for graphs. (CUuserObject_flags)

Enum values:

• USER_OBJECT_NO_DESTRUCTOR_SYNC - Indicates the destructor execution is not synchronized by any CUDA handle.

See Also:

• Constant Field Values

CU_GRAPH_USER_OBJECT_MOVE

public static final int CU_GRAPH_USER_OBJECT_MOVE

Flags for retaining user object references for graphs. (CUuserObjectRetain_flags)

Enum values:

• GRAPH_USER_OBJECT_MOVE - Transfer references from the caller rather than creating new references.

See Also:

• Constant Field Values

CUDA_GRAPH_INSTANTIATE_FLAG_AUTO_FREE_ON_LAUNCH

public static final int CUDA_GRAPH_INSTANTIATE_FLAG_AUTO_FREE_ON_LAUNCH

Flags for instantiating a graph. (CUgraphInstantiate_flags)

Enum values:

• CUDA_GRAPH_INSTANTIATE_FLAG_AUTO_FREE_ON_LAUNCH - Automatically free memory allocated in a graph before relaunching.

See Also:

• Constant Field Values

Method Details

getLibrary

public static SharedLibrary getLibrary()

Returns the NVCUDA SharedLibrary.

ncuGetErrorString

public static int ncuGetErrorString(int error,
 long pStr)

Unsafe version of: GetErrorString

cuGetErrorString

public static int cuGetErrorString(int error,
 PointerBuffer pStr)

Gets the string description of an error code.

Sets *pStr to the address of a NULL-terminated string description of the error code error. If the error code is not recognized, CUDA_ERROR_INVALID_VALUE will be returned and *pStr will be set to the NULL address.

Parameters:

error - error code to convert to string

pStr - address of the string pointer

ncuGetErrorName

public static int ncuGetErrorName(int error,
 long pStr)

Unsafe version of: GetErrorName

cuGetErrorName

public static int cuGetErrorName(int error,
 PointerBuffer pStr)

Gets the string representation of an error code enum name.

Sets *pStr to the address of a NULL-terminated string representation of the name of the enum error code error. If the error code is not recognized, CUDA_ERROR_INVALID_VALUE will be returned and *pStr will be set to the NULL address.

Parameters:

error - error code to convert to string

pStr - address of the string pointer

cuInit

public static int cuInit(int Flags)

Initialize the CUDA driver API.

Initializes the driver API and must be called before any other function from the driver API. Currently, the Flags parameter must be 0. If cuInit() has not been called, any function from the driver API will return CUDA_ERROR_NOT_INITIALIZED.

Parameters:

Flags - initialization flag for CUDA

ncuDriverGetVersion

public static int ncuDriverGetVersion(long driverVersion)

Unsafe version of: DriverGetVersion

cuDriverGetVersion

public static int cuDriverGetVersion(IntBuffer driverVersion)

Returns the latest CUDA version supported by driver.

Returns in *driverVersion the version of CUDA supported by the driver. The version is returned as (1000 × major + 10 × minor). For example, CUDA 9.2 would be represented by 9020.

This function automatically returns CUDA_ERROR_INVALID_VALUE if driverVersion is NULL.

Parameters:

driverVersion - returns the CUDA driver version

ncuDeviceGet

public static int ncuDeviceGet(long device,
 int ordinal)

Unsafe version of: DeviceGet

cuDeviceGet

public static int cuDeviceGet(IntBuffer device,
 int ordinal)

Returns a handle to a compute device.

Returns in *device a device handle given an ordinal in the range [0, cuDeviceGetCount()-1].

Parameters:

device - returned device handle

ordinal - device number to get handle for

ncuDeviceGetCount

public static int ncuDeviceGetCount(long count)

Unsafe version of: DeviceGetCount

cuDeviceGetCount

public static int cuDeviceGetCount(IntBuffer count)

Returns the number of compute-capable devices.

Returns in *count the number of devices with compute capability greater than or equal to 2.0 that are available for execution. If there is no such device, cuDeviceGetCount() returns 0.

Parameters:

count - returned number of compute-capable devices

ncuDeviceGetName

public static int ncuDeviceGetName(long name,
 int len,
 int dev)

Unsafe version of: DeviceGetName

Parameters:

len - maximum length of string to store in name

cuDeviceGetName

public static int cuDeviceGetName(ByteBuffer name,
 int dev)

Returns an identifer string for the device.

Returns an ASCII string identifying the device dev in the NULL-terminated string pointed to by name. len specifies the maximum length of the string that may be returned.

Parameters:

name - returned identifier string for the device

dev - device to get identifier string for

ncuDeviceGetUuid

public static int ncuDeviceGetUuid(long uuid,
 int dev)

Unsafe version of: DeviceGetUuid

cuDeviceGetUuid

public static int cuDeviceGetUuid(CUuuid uuid,
 int dev)

Return an UUID for the device.

Note there is a later version of this API, DeviceGetUuid_v2. It will supplant this version in 12.0, which is retained for minor version. compatibility.

Returns 16-octets identifing the device dev in the structure pointed by the uuid.

Parameters:

uuid - returned UUID

dev - device to get identifier string for

ncuDeviceGetUuid_v2

public static int ncuDeviceGetUuid_v2(long uuid,
 int dev)

Unsafe version of: DeviceGetUuid_v2

cuDeviceGetUuid_v2

public static int cuDeviceGetUuid_v2(CUuuid uuid,
 int dev)

Return an UUID for the device (11.4+).

Returns 16-octets identifing the device dev in the structure pointed by the uuid. If the device is in MIG mode, returns its MIG UUID which uniquely identifies the subscribed MIG compute instance.

Parameters:

uuid - returned UUID

dev - device to get identifier string for

ncuDeviceGetLuid

public static int ncuDeviceGetLuid(long luid,
 long deviceNodeMask,
 int dev)

Unsafe version of: DeviceGetLuid

cuDeviceGetLuid

public static int cuDeviceGetLuid(ByteBuffer luid,
 IntBuffer deviceNodeMask,
 int dev)

Return an LUID and device node mask for the device

Return identifying information (luid and deviceNodeMask) to allow matching device with graphics APIs.

Parameters:

luid - returned LUID

deviceNodeMask - returned device node mask

dev - device to get identifier string for

ncuDeviceTotalMem

public static int ncuDeviceTotalMem(long bytes,
 int dev)

Unsafe version of: DeviceTotalMem

cuDeviceTotalMem

public static int cuDeviceTotalMem(PointerBuffer bytes,
 int dev)

Returns the total amount of memory on the device

Returns in *bytes the total amount of memory available on the device dev in bytes.

Parameters:

bytes - returned memory available on device in bytes

dev - device handle

ncuDeviceGetTexture1DLinearMaxWidth

public static int ncuDeviceGetTexture1DLinearMaxWidth(long maxWidthInElements,
 int format,
 int numChannels,
 int dev)

Unsafe version of: DeviceGetTexture1DLinearMaxWidth

cuDeviceGetTexture1DLinearMaxWidth

public static int cuDeviceGetTexture1DLinearMaxWidth(PointerBuffer maxWidthInElements,
 int format,
 int numChannels,
 int dev)

Returns the maximum number of elements allocatable in a 1D linear texture for a given texture element size.

Returns in maxWidthInElements the maximum number of texture elements allocatable in a 1D linear texture for given format and numChannels.

Parameters:

maxWidthInElements - returned maximum number of texture elements allocatable for given format and numChannels

format - texture format

numChannels - number of channels per texture element

dev - device handle

ncuDeviceGetAttribute

public static int ncuDeviceGetAttribute(long pi,
 int attrib,
 int dev)

Unsafe version of: DeviceGetAttribute

cuDeviceGetAttribute

public static int cuDeviceGetAttribute(IntBuffer pi,
 int attrib,
 int dev)

Returns information about the device.

Returns in *pi the integer value of the attribute attrib on device dev. The supported attributes are:

Parameters:

pi - returned device attribute value

attrib - device attribute to query

dev - device handle

ncuDeviceGetNvSciSyncAttributes

public static int ncuDeviceGetNvSciSyncAttributes(long nvSciSyncAttrList,
 int dev,
 int flags)

Unsafe version of: DeviceGetNvSciSyncAttributes

cuDeviceGetNvSciSyncAttributes

public static int cuDeviceGetNvSciSyncAttributes(ByteBuffer nvSciSyncAttrList,
 int dev,
 int flags)

Return NvSciSync attributes that this device can support.

Returns in nvSciSyncAttrList, the properties of NvSciSync that this CUDA device, dev can support. The returned nvSciSyncAttrList can be used to create an NvSciSync object that matches this device's capabilities.

If NvSciSyncAttrKey_RequiredPerm field in nvSciSyncAttrList is already set this API will return CUDA_ERROR_INVALID_VALUE.

The applications should set nvSciSyncAttrList to a valid NvSciSyncAttrList failing which this API will return CUDA_ERROR_INVALID_HANDLE.

The flags controls how applications intends to use the NvSciSync created from the nvSciSyncAttrList. The valid flags are:

• CUDA_NVSCISYNC_ATTR_SIGNAL, specifies that the applications intends to signal an NvSciSync on this CUDA device.
• CUDA_NVSCISYNC_ATTR_WAIT, specifies that the applications intends to wait on an NvSciSync on this CUDA device.

At least one of these flags must be set, failing which the API returns CUDA_ERROR_INVALID_VALUE. Both the flags are orthogonal to one another: a developer may set both these flags that allows to set both wait and signal specific attributes in the same nvSciSyncAttrList.

Parameters:

nvSciSyncAttrList - return NvSciSync attributes supported

dev - valid Cuda Device to get NvSciSync attributes for

flags - flags describing NvSciSync usage

cuDeviceSetMemPool

public static int cuDeviceSetMemPool(int dev,
 long pool)

Sets the current memory pool of a device

The memory pool must be local to the specified device. MemAllocAsync allocates from the current mempool of the provided stream's device. By default, a device's current memory pool is its default memory pool.

Note

Use MemAllocFromPoolAsync to specify asynchronous allocations from a device different than the one the stream runs on.

ncuDeviceGetMemPool

public static int ncuDeviceGetMemPool(long pool,
 int dev)

Unsafe version of: DeviceGetMemPool

cuDeviceGetMemPool

public static int cuDeviceGetMemPool(PointerBuffer pool,
 int dev)

Gets the current mempool for a device.

Returns the last pool provided to DeviceSetMemPool for this device or the device's default memory pool if DeviceSetMemPool has never been called. By default the current mempool is the default mempool for a device. Otherwise the returned pool must have been set with DeviceSetMemPool.

ncuDeviceGetDefaultMemPool

public static int ncuDeviceGetDefaultMemPool(long pool_out,
 int dev)

Unsafe version of: DeviceGetDefaultMemPool

cuDeviceGetDefaultMemPool

public static int cuDeviceGetDefaultMemPool(PointerBuffer pool_out,
 int dev)

Returns the default mempool of a device.

The default mempool of a device contains device memory from that device.

cuFlushGPUDirectRDMAWrites

public static int cuFlushGPUDirectRDMAWrites(int target,
 int scope)

Blocks until remote writes are visible to the specified scope.

Blocks until GPUDirect RDMA writes to the target context via mappings created through APIs like nvidia_p2p_get_pages (see https://docs.nvidia.com/cuda/gpudirect-rdma for more information), are visible to the specified scope.

If the scope equals or lies within the scope indicated by DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING, the call will be a no-op and can be safely omitted for performance. This can be determined by comparing the numerical values between the two enums, with smaller scopes having smaller values.

Users may query support for this API via DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS.

Parameters:

target - the target of the operation, see CUflushGPUDirectRDMAWritesTarget

scope - the scope of the operation, see CUflushGPUDirectRDMAWritesScope

ncuDeviceGetProperties

public static int ncuDeviceGetProperties(long prop,
 int dev)

Unsafe version of: DeviceGetProperties

cuDeviceGetProperties

public static int cuDeviceGetProperties(CUdevprop prop,
 int dev)

Returns properties for a selected device.

Deprecated: This function was deprecated as of CUDA 5.0 and replaced by DeviceGetAttribute.

Returns in *prop the properties of device dev.

Parameters:

prop - returned properties of device

dev - device to get properties for

ncuDeviceComputeCapability

public static int ncuDeviceComputeCapability(long major,
 long minor,
 int dev)

Unsafe version of: DeviceComputeCapability

cuDeviceComputeCapability

public static int cuDeviceComputeCapability(IntBuffer major,
 IntBuffer minor,
 int dev)

Returns the compute capability of the device.

Deprecated: This function was deprecated as of CUDA 5.0 and its functionality superceded by DeviceGetAttribute.

Returns in *major and *minor the major and minor revision numbers that define the compute capability of the device dev.

Parameters:

major - major revision number

minor - minor revision number

dev - device handle

ncuDevicePrimaryCtxRetain

public static int ncuDevicePrimaryCtxRetain(long pctx,
 int dev)

Unsafe version of: DevicePrimaryCtxRetain

cuDevicePrimaryCtxRetain

public static int cuDevicePrimaryCtxRetain(PointerBuffer pctx,
 int dev)

Retain the primary context on the GPU.

Retains the primary context on the device. Once the user successfully retains the primary context, the primary context will be active and available to the user until the user releases it with DevicePrimaryCtxRelease or resets it with DevicePrimaryCtxReset. Unlike CtxCreate the newly retained context is not pushed onto the stack.

Retaining the primary context for the first time will fail with CUDA_ERROR_UNKNOWN if the compute mode of the device is COMPUTEMODE_PROHIBITED. The function DeviceGetAttribute can be used with DEVICE_ATTRIBUTE_COMPUTE_MODE to determine the compute mode of the device. The nvidia-smi tool can be used to set the compute mode for devices. Documentation for nvidia-smi can be obtained by passing a -h option to it.

Please note that the primary context always supports pinned allocations. Other flags can be specified by DevicePrimaryCtxSetFlags.

Parameters:

pctx - returned context handle of the new context

dev - device for which primary context is requested

cuDevicePrimaryCtxRelease

public static int cuDevicePrimaryCtxRelease(int dev)

Release the primary context on the GPU.

Releases the primary context interop on the device. A retained context should always be released once the user is done using it. The context is automatically reset once the last reference to it is released. This behavior is different when the primary context was retained by the CUDA runtime from CUDA 4.0 and earlier. In this case, the primary context remains always active.

Releasing a primary context that has not been previously retained will fail with CUDA_ERROR_INVALID_CONTEXT.

Please note that unlike CtxDestroy this method does not pop the context from stack in any circumstances.

Parameters:

dev - device which primary context is released

cuDevicePrimaryCtxSetFlags

public static int cuDevicePrimaryCtxSetFlags(int dev,
 int flags)

Set flags for the primary context.

Sets the flags for the primary context on the device overwriting perviously set ones.

The three LSBs of the flags parameter can be used to control how the OS thread, which owns the CUDA context at the time of an API call, interacts with the OS scheduler when waiting for results from the GPU. Only one of the scheduling flags can be set when creating a context:

• CTX_SCHED_SPIN: Instruct CUDA to actively spin when waiting for results from the GPU. This can decrease latency when waiting for the GPU, but may lower the performance of CPU threads if they are performing work in parallel with the CUDA thread.
• CTX_SCHED_YIELD: Instruct CUDA to yield its thread when waiting for results from the GPU. This can increase latency when waiting for the GPU, but can increase the performance of CPU threads performing work in parallel with the GPU.
• CTX_SCHED_BLOCKING_SYNC: Instruct CUDA to block the CPU thread on a synchronization primitive when waiting for the GPU to finish work.
• CTX_BLOCKING_SYNC: Instruct CUDA to block the CPU thread on a synchronization primitive when waiting for the GPU to finish work.

  Deprecated: This flag was deprecated as of CUDA 4.0 and was replaced with CTX_SCHED_BLOCKING_SYNC.

• CTX_SCHED_AUTO: The default value if the flags parameter is zero, uses a heuristic based on the number of active CUDA contexts in the process C and the number of logical processors in the system P. If C > P, then CUDA will yield to other OS threads when waiting for the GPU (CTX_SCHED_YIELD), otherwise CUDA will not yield while waiting for results and actively spin on the processor (CTX_SCHED_SPIN). Additionally, on Tegra devices, CTX_SCHED_AUTO uses a heuristic based on the power profile of the platform and may choose CTX_SCHED_BLOCKING_SYNC for low-powered devices.
• CTX_LMEM_RESIZE_TO_MAX: Instruct CUDA to not reduce local memory after resizing local memory for a kernel. This can prevent thrashing by local memory allocations when launching many kernels with high local memory usage at the cost of potentially increased memory usage.

  Deprecated: This flag is deprecated and the behavior enabled by this flag is now the default and cannot be disabled.

Parameters:

dev - device for which the primary context flags are set

flags - new flags for the device

ncuDevicePrimaryCtxGetState

public static int ncuDevicePrimaryCtxGetState(int dev,
 long flags,
 long active)

Unsafe version of: DevicePrimaryCtxGetState

cuDevicePrimaryCtxGetState

public static int cuDevicePrimaryCtxGetState(int dev,
 IntBuffer flags,
 IntBuffer active)

Get the state of the primary context.

Returns in *flags the flags for the primary context of dev, and in *active whether it is active. See DevicePrimaryCtxSetFlags for flag values.

Parameters:

dev - device to get primary context flags for

flags - pointer to store flags

active - pointer to store context state; 0 = inactive, 1 = active

cuDevicePrimaryCtxReset

public static int cuDevicePrimaryCtxReset(int dev)

Destroy all allocations and reset all state on the primary context.

Explicitly destroys and cleans up all resources associated with the current device in the current process.

Note that it is responsibility of the calling function to ensure that no other module in the process is using the device any more. For that reason it is recommended to use DevicePrimaryCtxRelease in most cases. However it is safe for other modules to call cuDevicePrimaryCtxRelease() even after resetting the device. Resetting the primary context does not release it, an application that has retained the primary context should explicitly release its usage.

Parameters:

dev - device for which primary context is destroyed

ncuDeviceGetExecAffinitySupport

public static int ncuDeviceGetExecAffinitySupport(long pi,
 int type,
 int dev)

Unsafe version of: DeviceGetExecAffinitySupport

cuDeviceGetExecAffinitySupport

public static int cuDeviceGetExecAffinitySupport(IntBuffer pi,
 int type,
 int dev)

Returns information about the execution affinity support of the device.

Returns in *pi whether execution affinity type type is supported by device dev. The supported types are:

• EXEC_AFFINITY_TYPE_SM_COUNT: 1 if context with limited SMs is supported by the device, or 0 if not;

Parameters:

pi - 1 if the execution affinity type type is supported by the device, or 0 if not

type - execution affinity type to query

dev - device handle

ncuCtxCreate

public static int ncuCtxCreate(long pctx,
 int flags,
 int dev)

Unsafe version of: CtxCreate

cuCtxCreate

public static int cuCtxCreate(PointerBuffer pctx,
 int flags,
 int dev)

Create a CUDA context.

Note

In most cases it is recommended to use DevicePrimaryCtxRetain.

Creates a new CUDA context and associates it with the calling thread. The flags parameter is described below. The context is created with a usage count of 1 and the caller of cuCtxCreate() must call CtxDestroy or when done using the context. If a context is already current to the thread, it is supplanted by the newly created context and may be restored by a subsequent call to CtxPopCurrent.

The three LSBs of the flags parameter can be used to control how the OS thread, which owns the CUDA context at the time of an API call, interacts with the OS scheduler when waiting for results from the GPU. Only one of the scheduling flags can be set when creating a context:

• CTX_SCHED_SPIN: Instruct CUDA to actively spin when waiting for results from the GPU. This can decrease latency when waiting for the GPU, but may lower the performance of CPU threads if they are performing work in parallel with the CUDA thread.
• CTX_SCHED_YIELD: Instruct CUDA to yield its thread when waiting for results from the GPU. This can increase latency when waiting for the GPU, but can increase the performance of CPU threads performing work in parallel with the GPU.
• CTX_SCHED_BLOCKING_SYNC: Instruct CUDA to block the CPU thread on a synchronization primitive when waiting for the GPU to finish work.
• CTX_BLOCKING_SYNC: Instruct CUDA to block the CPU thread on a synchronization primitive when waiting for the GPU to finish work.

  Deprecated: This flag was deprecated as of CUDA 4.0 and was replaced with CTX_SCHED_BLOCKING_SYNC.

• CTX_SCHED_AUTO: The default value if the flags parameter is zero, uses a heuristic based on the number of active CUDA contexts in the process C and the number of logical processors in the system P. If C > P, then CUDA will yield to other OS threads when waiting for the GPU (CTX_SCHED_YIELD), otherwise CUDA will not yield while waiting for results and actively spin on the processor (CTX_SCHED_SPIN). Additionally, on Tegra devices, CTX_SCHED_AUTO uses a heuristic based on the power profile of the platform and may choose CTX_SCHED_BLOCKING_SYNC for low-powered devices.
• CTX_MAP_HOST: Instruct CUDA to support mapped pinned allocations. This flag must be set in order to allocate pinned host memory that is accessible to the GPU.
• CTX_LMEM_RESIZE_TO_MAX: Instruct CUDA to not reduce local memory after resizing local memory for a kernel. This can prevent thrashing by local memory allocations when launching many kernels with high local memory usage at the cost of potentially increased memory usage.

  Deprecated: This flag is deprecated and the behavior enabled by this flag is now the default and cannot be disabled. Instead, the per-thread stack size can be controlled with CtxSetLimit.

Context creation will fail with CUDA_ERROR_UNKNOWN if the compute mode of the device is COMPUTEMODE_PROHIBITED. The function DeviceGetAttribute can be used with DEVICE_ATTRIBUTE_COMPUTE_MODE to determine the compute mode of the device. The nvidia-smi tool can be used to set the compute mode for * devices. Documentation for nvidia-smi can be obtained by passing a -h option to it.

Parameters:

pctx - returned context handle of the new context

flags - context creation flags

dev - device to create context on

ncuCtxCreate_v3

public static int ncuCtxCreate_v3(long pctx,
 long paramsArray,
 int numParams,
 int flags,
 int dev)

Unsafe version of: CtxCreate_v3

Parameters:

numParams - number of execution affinity parameters

cuCtxCreate_v3

public static int cuCtxCreate_v3(PointerBuffer pctx,
 CUexecAffinityParam.Buffer paramsArray,
 int flags,
 int dev)

Create a CUDA context with execution affinity.

Creates a new CUDA context with execution affinity and associates it with the calling thread. The paramsArray and flags parameter are described below. The context is created with a usage count of 1 and the caller of CtxCreate must call CtxDestroy or when done using the context. If a context is already current to the thread, it is supplanted by the newly created context and may be restored by a subsequent call to CtxPopCurrent.

The type and the amount of execution resource the context can use is limited by paramsArray and numParams. The paramsArray is an array of CUexecAffinityParam and the numParams describes the size of the array. If two CUexecAffinityParam in the array have the same type, the latter execution affinity parameter overrides the former execution affinity parameter. The supported execution affinity types are:

• EXEC_AFFINITY_TYPE_SM_COUNT limits the portion of SMs that the context can use. The portion of SMs is specified as the number of SMs via CUexecAffinitySmCount. This limit will be internally rounded up to the next hardware-supported amount. Hence, it is imperative to query the actual execution affinity of the context via CtxGetExecAffinity) after context creation. Currently, this attribute is only supported under Volta+ MPS.

The three LSBs of the flags parameter can be used to control how the OS thread, which owns the CUDA context at the time of an API call, interacts with the OS scheduler when waiting for results from the GPU. Only one of the scheduling flags can be set when creating a context:

• CTX_SCHED_SPIN: Instruct CUDA to actively spin when waiting for results from the GPU. This can decrease latency when waiting for the GPU, but may lower the performance of CPU threads if they are performing work in parallel with the CUDA thread.
• CTX_SCHED_YIELD: Instruct CUDA to yield its thread when waiting for results from the GPU. This can increase latency when waiting for the GPU, but can increase the performance of CPU threads performing work in parallel with the GPU.
• CTX_SCHED_BLOCKING_SYNC: Instruct CUDA to block the CPU thread on a synchronization primitive when waiting for the GPU to finish work.
• CTX_BLOCKING_SYNC: Instruct CUDA to block the CPU thread on a synchronization primitive when waiting for the GPU to finish work.

  Deprecated: This flag was deprecated as of CUDA 4.0 and was replaced with CTX_SCHED_BLOCKING_SYNC.

• CTX_SCHED_AUTO: The default value if the flags parameter is zero, uses a heuristic based on the number of active CUDA contexts in the process C and the number of logical processors in the system P. If C > P, then CUDA will yield to other OS threads when waiting for the GPU (CTX_SCHED_YIELD), otherwise CUDA will not yield while waiting for results and actively spin on the processor (CTX_SCHED_SPIN). Additionally, on Tegra devices, CTX_SCHED_AUTO uses a heuristic based on the power profile of the platform and may choose CTX_SCHED_BLOCKING_SYNC for low-powered devices.
• CTX_MAP_HOST: Instruct CUDA to support mapped pinned allocations. This flag must be set in order to allocate pinned host memory that is accessible to the GPU.
• CTX_LMEM_RESIZE_TO_MAX: Instruct CUDA to not reduce local memory after resizing local memory for a kernel. This can prevent thrashing by local memory allocations when launching many kernels with high local memory usage at the cost of potentially increased memory usage.

  Deprecated: This flag is deprecated and the behavior enabled by this flag is now the default and cannot be disabled. Instead, the per-thread stack size can be controlled with CtxSetLimit.

Context creation will fail with CUDA_ERROR_UNKNOWN if the compute mode of the device is COMPUTEMODE_PROHIBITED. The function DeviceGetAttribute can be used with DEVICE_ATTRIBUTE_COMPUTE_MODE to determine the compute mode of the device. The nvidia-smi tool can be used to set the compute mode for * devices. Documentation for nvidia-smi can be obtained by passing a -h option to it.

Parameters:

pctx - returned context handle of the new context

paramsArray - execution affinity parameters

flags - context creation flags

dev - device to create context on

cuCtxDestroy

public static int cuCtxDestroy(long ctx)

Destroy a CUDA context.

Destroys the CUDA context specified by ctx. The context ctx will be destroyed regardless of how many threads it is current to. It is the responsibility of the calling function to ensure that no API call issues using ctx while cuCtxDestroy() is executing.

Destroys and cleans up all resources associated with the context. It is the caller's responsibility to ensure that the context or its resources are not accessed or passed in subsequent API calls and doing so will result in undefined behavior. These resources include CUDA types such as CUmodule, CUfunction, CUstream, CUevent, CUarray, CUmipmappedArray, CUtexObject, CUsurfObject, CUtexref, CUsurfref, CUgraphicsResource, CUlinkState, CUexternalMemory and CUexternalSemaphore.

If ctx is current to the calling thread then ctx will also be popped from the current thread's context stack (as though CtxPopCurrent were called). If ctx is current to other threads, then ctx will remain current to those threads, and attempting to access ctx from those threads will result in the error CUDA_ERROR_CONTEXT_IS_DESTROYED.

Parameters:

ctx - context to destroy

cuCtxPushCurrent

public static int cuCtxPushCurrent(long ctx)

Pushes a context on the current CPU thread.

Pushes the given context ctx onto the CPU thread's stack of current contexts. The specified context becomes the CPU thread's current context, so all CUDA functions that operate on the current context are affected.

The previous current context may be made current again by calling CtxDestroy or CtxPopCurrent.

Parameters:

ctx - context to push

ncuCtxPopCurrent

public static int ncuCtxPopCurrent(long pctx)

Unsafe version of: CtxPopCurrent

cuCtxPopCurrent

public static int cuCtxPopCurrent(PointerBuffer pctx)

Pops the current CUDA context from the current CPU thread.

Pops the current CUDA context from the CPU thread and passes back the old context handle in *pctx. That context may then be made current to a different CPU thread by calling CtxPushCurrent.

If a context was current to the CPU thread before CtxCreate or CtxPushCurrent was called, this function makes that context current to the CPU thread again.

Parameters:

pctx - returned new context handle

cuCtxSetCurrent

public static int cuCtxSetCurrent(long ctx)

Binds the specified CUDA context to the calling CPU thread.

Binds the specified CUDA context to the calling CPU thread. If ctx is NULL then the CUDA context previously bound to the calling CPU thread is unbound and CUDA_SUCCESS is returned.

If there exists a CUDA context stack on the calling CPU thread, this will replace the top of that stack with ctx. If ctx is NULL then this will be equivalent to popping the top of the calling CPU thread's CUDA context stack (or a no-op if the calling CPU thread's CUDA context stack is empty).

Parameters:

ctx - context to bind to the calling CPU thread

ncuCtxGetCurrent

public static int ncuCtxGetCurrent(long pctx)

Unsafe version of: CtxGetCurrent

cuCtxGetCurrent

public static int cuCtxGetCurrent(PointerBuffer pctx)

Returns the CUDA context bound to the calling CPU thread.

Returns in *pctx the CUDA context bound to the calling CPU thread. If no context is bound to the calling CPU thread then *pctx is set to NULL and CUDA_SUCCESS is returned.

Parameters:

pctx - returned context handle

ncuCtxGetDevice

public static int ncuCtxGetDevice(long device)

Unsafe version of: CtxGetDevice

cuCtxGetDevice

public static int cuCtxGetDevice(IntBuffer device)

Returns the device ID for the current context.

Returns in *device the ordinal of the current context's device.

Parameters:

device - returned device ID for the current context

ncuCtxGetFlags

public static int ncuCtxGetFlags(long flags)

Unsafe version of: CtxGetFlags

cuCtxGetFlags

public static int cuCtxGetFlags(IntBuffer flags)

Returns the flags for the current context.

Returns in *flags the flags of the current context. See CtxCreate for flag values.

Parameters:

flags - pointer to store flags of current context

cuCtxSynchronize

public static int cuCtxSynchronize()

Block for a context's tasks to complete.

Blocks until the device has completed all preceding requested tasks. cuCtxSynchronize() returns an error if one of the preceding tasks failed. If the context was created with the CTX_SCHED_BLOCKING_SYNC flag, the CPU thread will block until the GPU context has finished its work.

cuCtxSetLimit

public static int cuCtxSetLimit(int limit,
 long value)

Set resource limits.

Setting limit to value is a request by the application to update the current limit maintained by the context. The driver is free to modify the requested value to meet h/w requirements (this could be clamping to minimum or maximum values, rounding up to nearest element size, etc). The application can use CtxGetLimit to find out exactly what the limit has been set to.

Setting each CUlimit has its own specific restrictions, so each is discussed here.

• LIMIT_STACK_SIZE controls the stack size in bytes of each GPU thread. The driver automatically increases the per-thread stack size for each kernel launch as needed. This size isn't reset back to the original value after each launch. Setting this value will take effect immediately, and if necessary, the device will block until all preceding requested tasks are complete.
• LIMIT_PRINTF_FIFO_SIZE controls the size in bytes of the FIFO used by the printf() device system call. Setting LIMIT_PRINTF_FIFO_SIZE must be performed before launching any kernel that uses the printf() device system call, otherwise CUDA_ERROR_INVALID_VALUE will be returned.
• LIMIT_MALLOC_HEAP_SIZE controls the size in bytes of the heap used by the malloc() and free() device system calls. Setting CU_LIMIT_MALLOC_HEAP_SIZE must be performed before launching any kernel that uses the malloc() or free() device system calls, otherwise CUDA_ERROR_INVALID_VALUE will be returned.
• LIMIT_DEV_RUNTIME_SYNC_DEPTH controls the maximum nesting depth of a grid at which a thread can safely call cudaDeviceSynchronize(). Setting this limit must be performed before any launch of a kernel that uses the device runtime and calls cudaDeviceSynchronize() above the default sync depth, two levels of grids. Calls to cudaDeviceSynchronize() will fail with error code cudaErrorSyncDepthExceeded if the limitation is violated. This limit can be set smaller than the default or up the maximum launch depth of 24. When setting this limit, keep in mind that additional levels of sync depth require the driver to reserve large amounts of device memory which can no longer be used for user allocations. If these reservations of device memory fail, cuCtxSetLimit() will return CUDA_ERROR_OUT_OF_MEMORY, and the limit can be reset to a lower value. This limit is only applicable to devices of compute capability 3.5 and higher. Attempting to set this limit on devices of compute capability less than 3.5 will result in the error CUDA_ERROR_UNSUPPORTED_LIMIT being returned.
• LIMIT_DEV_RUNTIME_PENDING_LAUNCH_COUNT controls the maximum number of outstanding device runtime launches that can be made from the current context. A grid is outstanding from the point of launch up until the grid is known to have been completed. Device runtime launches which violate this limitation fail and return cudaErrorLaunchPendingCountExceeded when cudaGetLastError() is called after launch. If more pending launches than the default (2048 launches) are needed for a module using the device runtime, this limit can be increased. Keep in mind that being able to sustain additional pending launches will require the driver to reserve larger amounts of device memory upfront which can no longer be used for allocations. If these reservations fail, cuCtxSetLimit() will return CUDA_ERROR_OUT_OF_MEMORY, and the limit can be reset to a lower value. This limit is only applicable to devices of compute capability 3.5 and higher. Attempting to set this limit on devices of compute capability less than 3.5 will result in the error CUDA_ERROR_UNSUPPORTED_LIMIT being returned.
• LIMIT_MAX_L2_FETCH_GRANULARITY controls the L2 cache fetch granularity. Values can range from 0B to 128B. This is purely a performence hint and it can be ignored or clamped depending on the platform.
• LIMIT_PERSISTING_L2_CACHE_SIZE controls size in bytes availabe for persisting L2 cache. This is purely a performance hint and it can be ignored or clamped depending on the platform.

Parameters:

limit - limit to set

value - size of limit

ncuCtxGetLimit

public static int ncuCtxGetLimit(long pvalue,
 int limit)

Unsafe version of: CtxGetLimit

cuCtxGetLimit

public static int cuCtxGetLimit(PointerBuffer pvalue,
 int limit)

Returns resource limits.

Returns in *pvalue the current size of limit.

Parameters:

pvalue - returned size of limit

limit - limit to query

ncuCtxGetCacheConfig

public static int ncuCtxGetCacheConfig(long pconfig)

Unsafe version of: CtxGetCacheConfig

cuCtxGetCacheConfig

public static int cuCtxGetCacheConfig(IntBuffer pconfig)

Returns the preferred cache configuration for the current context.

On devices where the L1 cache and shared memory use the same hardware resources, this function returns through pconfig the preferred cache configuration for the current context. This is only a preference. The driver will use the requested configuration if possible, but it is free to choose a different configuration if required to execute functions.

This will return a pconfig of FUNC_CACHE_PREFER_NONE on devices where the size of the L1 cache and shared memory are fixed.

Parameters:

pconfig - returned cache configuration

cuCtxSetCacheConfig

public static int cuCtxSetCacheConfig(int config)

Sets the preferred cache configuration for the current context.

On devices where the L1 cache and shared memory use the same hardware resources, this sets through config the preferred cache configuration for the current context. This is only a preference. The driver will use the requested configuration if possible, but it is free to choose a different configuration if required to execute the function. Any function preference set via cuFuncSetCacheConfig() will be preferred over this context-wide setting. Setting the context-wide cache configuration to FUNC_CACHE_PREFER_NONE will cause subsequent kernel launches to prefer to not change the cache configuration unless required to launch the kernel.

This setting does nothing on devices where the size of the L1 cache and shared memory are fixed.

Launching a kernel with a different preference than the most recent preference setting may insert a device-side synchronization point.

Parameters:

config - requested cache configuration

ncuCtxGetSharedMemConfig

public static int ncuCtxGetSharedMemConfig(long pConfig)

Unsafe version of: CtxGetSharedMemConfig

cuCtxGetSharedMemConfig

public static int cuCtxGetSharedMemConfig(IntBuffer pConfig)

Returns the current shared memory configuration for the current context.

This function will return in pConfig the current size of shared memory banks in the current context. On devices with configurable shared memory banks, CtxSetSharedMemConfig can be used to change this setting, so that all subsequent kernel launches will by default use the new bank size. When cuCtxGetSharedMemConfig is called on devices without configurable shared memory, it will return the fixed bank size of the hardware.

Parameters:

pConfig - returned shared memory configuration

cuCtxSetSharedMemConfig

public static int cuCtxSetSharedMemConfig(int config)

Sets the shared memory configuration for the current context.

On devices with configurable shared memory banks, this function will set the context's shared memory bank size which is used for subsequent kernel launches.

Changed the shared memory configuration between launches may insert a device side synchronization point between those launches.

Changing the shared memory bank size will not increase shared memory usage or affect occupancy of kernels, but may have major effects on performance. Larger bank sizes will allow for greater potential bandwidth to shared memory, but will change what kinds of accesses to shared memory will result in bank conflicts.

This function will do nothing on devices with fixed shared memory bank size.

Parameters:

config - requested shared memory configuration

ncuCtxGetApiVersion

public static int ncuCtxGetApiVersion(long ctx,
 long version)

Unsafe version of: CtxGetApiVersion

cuCtxGetApiVersion

public static int cuCtxGetApiVersion(long ctx,
 IntBuffer version)

Gets the context's API version.

Returns a version number in version corresponding to the capabilities of the context (e.g. 3010 or 3020), which library developers can use to direct callers to a specific API version. If ctx is NULL, returns the API version used to create the currently bound context.

Note that new API versions are only introduced when context capabilities are changed that break binary compatibility, so the API version and driver version may be different. For example, it is valid for the API version to be 3020 while the driver version is 4020.

Parameters:

ctx - context to check

version - pointer to version

ncuCtxGetStreamPriorityRange

public static int ncuCtxGetStreamPriorityRange(long leastPriority,
 long greatestPriority)

Unsafe version of: CtxGetStreamPriorityRange

cuCtxGetStreamPriorityRange

public static int cuCtxGetStreamPriorityRange(@Nullable
 IntBuffer leastPriority,
 @Nullable
 IntBuffer greatestPriority)

Returns numerical values that correspond to the least and greatest stream priorities.

Returns in *leastPriority and *greatestPriority the numerical values that correspond to the least and greatest stream priorities respectively. Stream priorities follow a convention where lower numbers imply greater priorities. The range of meaningful stream priorities is given by [ *greatestPriority, *leastPriority]. If the user attempts to create a stream with a priority value that is outside the meaningful range as specified by this API, the priority is automatically clamped down or up to either *leastPriority or *greatestPriority respectively. See StreamCreateWithPriority for details on creating a priority stream. A NULL may be passed in for *leastPriority or greatestPriority if the value is not desired.

This function will return 0 in both *leastPriority and *greatestPriority if the current context's device does not support stream priorities (see DeviceGetAttribute).

Parameters:

leastPriority - pointer to an int in which the numerical value for least stream priority is returned

greatestPriority - pointer to an int in which the numerical value for greatest stream priority is returned

cuCtxResetPersistingL2Cache

public static int cuCtxResetPersistingL2Cache()

Resets all persisting lines in cache to normal status.

Takes effect on function return.

ncuCtxGetExecAffinity

public static int ncuCtxGetExecAffinity(long pExecAffinity,
 int type)

Unsafe version of: CtxGetExecAffinity

cuCtxGetExecAffinity

public static int cuCtxGetExecAffinity(CUexecAffinityParam.Buffer pExecAffinity,
 int type)

Returns the execution affinity setting for the current context.

Returns in *pExecAffinity the current value of type.

Parameters:

pExecAffinity - returned execution affinity

type - execution affinity type to query

ncuCtxAttach

public static int ncuCtxAttach(long pctx,
 int flags)

Unsafe version of: CtxAttach

cuCtxAttach

public static int cuCtxAttach(PointerBuffer pctx,
 int flags)

Increment a context's usage-count.

Deprecated: Note that this function is deprecated and should not be used.

Increments the usage count of the context and passes back a context handle in *pctx that must be passed to CtxDetach when the application is done with the context. cuCtxAttach() fails if there is no context current to the thread.

Currently, the flags parameter must be 0.

Parameters:

pctx - returned context handle of the current context

flags - context attach flags (must be 0)

cuCtxDetach

public static int cuCtxDetach(long ctx)

Decrement a context's usage-count

Deprecated: Note that this function is deprecated and should not be used.

Decrements the usage count of the context ctx, and destroys the context if the usage count goes to 0. The context must be a handle that was passed back by CtxCreate or CtxAttach, and must be current to the calling thread.

Parameters:

ctx - context to destroy

ncuModuleLoad

public static int ncuModuleLoad(long module,
 long fname)

Unsafe version of: ModuleLoad

cuModuleLoad

public static int cuModuleLoad(PointerBuffer module,
 ByteBuffer fname)

Loads a compute module.

Takes a filename fname and loads the corresponding module module into the current context. The CUDA driver API does not attempt to lazily allocate the resources needed by a module; if the memory for functions and data (constant and global) needed by the module cannot be allocated, cuModuleLoad() fails. The file should be a cubin file as output by nvcc, or a PTX file either as output by nvcc or handwritten, or a fatbin file as output by nvcc from toolchain 4.0 or later.

Parameters:

module - returned module

fname - filename of module to load

cuModuleLoad

public static int cuModuleLoad(PointerBuffer module,
 CharSequence fname)

Loads a compute module.

Takes a filename fname and loads the corresponding module module into the current context. The CUDA driver API does not attempt to lazily allocate the resources needed by a module; if the memory for functions and data (constant and global) needed by the module cannot be allocated, cuModuleLoad() fails. The file should be a cubin file as output by nvcc, or a PTX file either as output by nvcc or handwritten, or a fatbin file as output by nvcc from toolchain 4.0 or later.

Parameters:

module - returned module

fname - filename of module to load

ncuModuleLoadData

public static int ncuModuleLoadData(long module,
 long image)

Unsafe version of: ModuleLoadData

cuModuleLoadData

public static int cuModuleLoadData(PointerBuffer module,
 ByteBuffer image)

Load a module's data.

Takes a pointer image and loads the corresponding module module into the current context. The pointer may be obtained by mapping a cubin or PTX or fatbin file, passing a cubin or PTX or fatbin file as a NULL-terminated text string, or incorporating a cubin or fatbin object into the executable resources and using operating system calls such as Windows FindResource() to obtain the pointer.

Parameters:

module - returned module

image - module data to load

ncuModuleLoadDataEx

public static int ncuModuleLoadDataEx(long module,
 long image,
 int numOptions,
 long options,
 long optionValues)

Unsafe version of: ModuleLoadDataEx

Parameters:

numOptions - number of options

cuModuleLoadDataEx

public static int cuModuleLoadDataEx(PointerBuffer module,
 ByteBuffer image,
 @Nullable
 IntBuffer options,
 @Nullable
 PointerBuffer optionValues)

Load a module's data with options.

Takes a pointer image and loads the corresponding module module into the current context. The pointer may be obtained by mapping a cubin or PTX or fatbin file, passing a cubin or PTX or fatbin file as a NULL-terminated text string, or incorporating a cubin or fatbin object into the executable resources and using operating system calls such as Windows FindResource() to obtain the pointer. Options are passed as an array via options and any corresponding parameters are passed in optionValues. The number of total options is supplied via numOptions. Any outputs will be returned via optionValues.

Parameters:

module - returned module

image - module data to load

options - options for JIT

optionValues - option values for JIT

ncuModuleLoadFatBinary

public static int ncuModuleLoadFatBinary(long module,
 long fatCubin)

Unsafe version of: ModuleLoadFatBinary

cuModuleLoadFatBinary

public static int cuModuleLoadFatBinary(PointerBuffer module,
 ByteBuffer fatCubin)

Load a module's data.

Takes a pointer fatCubin and loads the corresponding module module into the current context. The pointer represents a fat binary object, which is a collection of different cubin and/or PTX files, all representing the same device code, but compiled and optimized for different architectures.

Prior to CUDA 4.0, there was no documented API for constructing and using fat binary objects by programmers. Starting with CUDA 4.0, fat binary objects can be constructed by providing the -fatbin option to nvcc. More information can be found in the nvcc document.

Parameters:

module - returned module

fatCubin - fat binary to load

cuModuleUnload

public static int cuModuleUnload(long hmod)

Unloads a module.

Unloads a module hmod from the current context.

Parameters:

hmod - module to unload

ncuModuleGetFunction

public static int ncuModuleGetFunction(long hfunc,
 long hmod,
 long name)

Unsafe version of: ModuleGetFunction

cuModuleGetFunction

public static int cuModuleGetFunction(PointerBuffer hfunc,
 long hmod,
 ByteBuffer name)

Returns a function handle.

Returns in *hfunc the handle of the function of name name located in module hmod. If no function of that name exists, cuModuleGetFunction() returns CUDA_ERROR_NOT_FOUND.

Parameters:

hfunc - returned function handle

hmod - module to retrieve function from

name - name of function to retrieve

cuModuleGetFunction

public static int cuModuleGetFunction(PointerBuffer hfunc,
 long hmod,
 CharSequence name)

Returns a function handle.

Returns in *hfunc the handle of the function of name name located in module hmod. If no function of that name exists, cuModuleGetFunction() returns CUDA_ERROR_NOT_FOUND.

Parameters:

hfunc - returned function handle

hmod - module to retrieve function from

name - name of function to retrieve

ncuModuleGetGlobal

public static int ncuModuleGetGlobal(long dptr,
 long bytes,
 long hmod,
 long name)

Unsafe version of: ModuleGetGlobal

cuModuleGetGlobal

public static int cuModuleGetGlobal(@Nullable
 PointerBuffer dptr,
 @Nullable
 PointerBuffer bytes,
 long hmod,
 ByteBuffer name)

Returns a global pointer from a module.

Returns in *dptr and *bytes the base pointer and size of the global of name name located in module hmod. If no variable of that name exists, cuModuleGetGlobal() returns CUDA_ERROR_NOT_FOUND. Both parameters dptr and bytes are optional. If one of them is NULL, it is ignored.

Parameters:

dptr - returned global device pointer

bytes - returned global size in bytes

hmod - module to retrieve global from

name - name of global to retrieve

cuModuleGetGlobal

public static int cuModuleGetGlobal(@Nullable
 PointerBuffer dptr,
 @Nullable
 PointerBuffer bytes,
 long hmod,
 CharSequence name)

Returns a global pointer from a module.

Returns in *dptr and *bytes the base pointer and size of the global of name name located in module hmod. If no variable of that name exists, cuModuleGetGlobal() returns CUDA_ERROR_NOT_FOUND. Both parameters dptr and bytes are optional. If one of them is NULL, it is ignored.

Parameters:

dptr - returned global device pointer

bytes - returned global size in bytes

hmod - module to retrieve global from

name - name of global to retrieve

ncuModuleGetTexRef

public static int ncuModuleGetTexRef(long pTexRef,
 long hmod,
 long name)

Unsafe version of: ModuleGetTexRef

cuModuleGetTexRef

public static int cuModuleGetTexRef(PointerBuffer pTexRef,
 long hmod,
 ByteBuffer name)

Returns a handle to a texture reference.

Returns in *pTexRef the handle of the texture reference of name name in the module hmod. If no texture reference of that name exists, cuModuleGetTexRef() returns CUDA_ERROR_NOT_FOUND. This texture reference handle should not be destroyed, since it will be destroyed when the module is unloaded.

Parameters:

pTexRef - returned texture reference

hmod - module to retrieve texture reference from

name - name of texture reference to retrieve

cuModuleGetTexRef

public static int cuModuleGetTexRef(PointerBuffer pTexRef,
 long hmod,
 CharSequence name)

Returns a handle to a texture reference.

Returns in *pTexRef the handle of the texture reference of name name in the module hmod. If no texture reference of that name exists, cuModuleGetTexRef() returns CUDA_ERROR_NOT_FOUND. This texture reference handle should not be destroyed, since it will be destroyed when the module is unloaded.

Parameters:

pTexRef - returned texture reference

hmod - module to retrieve texture reference from

name - name of texture reference to retrieve

ncuModuleGetSurfRef

public static int ncuModuleGetSurfRef(long pSurfRef,
 long hmod,
 long name)

Unsafe version of: ModuleGetSurfRef

cuModuleGetSurfRef

public static int cuModuleGetSurfRef(PointerBuffer pSurfRef,
 long hmod,
 ByteBuffer name)

Returns a handle to a surface reference.

Returns in *pSurfRef the handle of the surface reference of name name in the module hmod. If no surface reference of that name exists, cuModuleGetSurfRef() returns CUDA_ERROR_NOT_FOUND.

Parameters:

pSurfRef - returned surface reference

hmod - module to retrieve surface reference from

name - name of surface reference to retrieve

cuModuleGetSurfRef

public static int cuModuleGetSurfRef(PointerBuffer pSurfRef,
 long hmod,
 CharSequence name)

Returns a handle to a surface reference.

Returns in *pSurfRef the handle of the surface reference of name name in the module hmod. If no surface reference of that name exists, cuModuleGetSurfRef() returns CUDA_ERROR_NOT_FOUND.

Parameters:

pSurfRef - returned surface reference

hmod - module to retrieve surface reference from

name - name of surface reference to retrieve

ncuLinkCreate

public static int ncuLinkCreate(int numOptions,
 long options,
 long optionValues,
 long stateOut)

Unsafe version of: LinkCreate

Parameters:

numOptions - size of options arrays

cuLinkCreate

public static int cuLinkCreate(IntBuffer options,
 PointerBuffer optionValues,
 PointerBuffer stateOut)

Creates a pending JIT linker invocation.

If the call is successful, the caller owns the returned CUlinkState, which should eventually be destroyed with LinkDestroy. The device code machine size (32 or 64 bit) will match the calling application.

Both linker and compiler options may be specified. Compiler options will be applied to inputs to this linker action which must be compiled from PTX. The options JIT_WALL_TIME, JIT_INFO_LOG_BUFFER_SIZE_BYTES, and JIT_ERROR_LOG_BUFFER_SIZE_BYTES will accumulate data until the CUlinkState is destroyed.

optionValues must remain valid for the life of the CUlinkState if output options are used. No other references to inputs are maintained after this call returns.

Parameters:

options - array of linker and compiler options

optionValues - array of option values, each cast to void *

stateOut - on success, this will contain a CUlinkState to specify and complete this action

ncuLinkAddData

public static int ncuLinkAddData(long state,
 int type,
 long data,
 long size,
 long name,
 int numOptions,
 long options,
 long optionValues)

Unsafe version of: LinkAddData

Parameters:

size - the length of the input data

numOptions - size of options

cuLinkAddData

public static int cuLinkAddData(long state,
 int type,
 ByteBuffer data,
 ByteBuffer name,
 IntBuffer options,
 PointerBuffer optionValues)

Add an input to a pending linker invocation.

Ownership of data is retained by the caller. No reference is retained to any inputs after this call returns.

This method accepts only compiler options, which are used if the data must be compiled from PTX, and does not accept any of JIT_WALL_TIME, JIT_INFO_LOG_BUFFER, JIT_ERROR_LOG_BUFFER, JIT_TARGET_FROM_CUCONTEXT, or JIT_TARGET.

Parameters:

state - a pending linker action

type - the type of the input data

data - the input data. PTX must be NULL-terminated.

name - an optional name for this input in log messages

options - options to be applied only for this input (overrides options from LinkCreate)

optionValues - array of option values, each cast to void *

cuLinkAddData

public static int cuLinkAddData(long state,
 int type,
 ByteBuffer data,
 CharSequence name,
 IntBuffer options,
 PointerBuffer optionValues)

Add an input to a pending linker invocation.

Ownership of data is retained by the caller. No reference is retained to any inputs after this call returns.

This method accepts only compiler options, which are used if the data must be compiled from PTX, and does not accept any of JIT_WALL_TIME, JIT_INFO_LOG_BUFFER, JIT_ERROR_LOG_BUFFER, JIT_TARGET_FROM_CUCONTEXT, or JIT_TARGET.

Parameters:

state - a pending linker action

type - the type of the input data

data - the input data. PTX must be NULL-terminated.

name - an optional name for this input in log messages

options - options to be applied only for this input (overrides options from LinkCreate)

optionValues - array of option values, each cast to void *

ncuLinkAddFile

public static int ncuLinkAddFile(long state,
 int type,
 long path,
 int numOptions,
 long options,
 long optionValues)

Unsafe version of: LinkAddFile

Parameters:

numOptions - size of options

cuLinkAddFile

public static int cuLinkAddFile(long state,
 int type,
 ByteBuffer path,
 IntBuffer options,
 PointerBuffer optionValues)

Add a file input to a pending linker invocation.

No reference is retained to any inputs after this call returns.

This method accepts only compiler options, which are used if the input must be compiled from PTX, and does not accept any of JIT_WALL_TIME, JIT_INFO_LOG_BUFFER, JIT_ERROR_LOG_BUFFER, JIT_TARGET_FROM_CUCONTEXT, or JIT_TARGET.

This method is equivalent to invoking LinkAddData on the contents of the file.

Parameters:

state - a pending linker action

type - the type of the input data

path - path to the input file

options - options to be applied only for this input (overrides options from LinkCreate)

optionValues - array of option values, each cast to void *

cuLinkAddFile

public static int cuLinkAddFile(long state,
 int type,
 CharSequence path,
 IntBuffer options,
 PointerBuffer optionValues)

Add a file input to a pending linker invocation.

No reference is retained to any inputs after this call returns.

This method accepts only compiler options, which are used if the input must be compiled from PTX, and does not accept any of JIT_WALL_TIME, JIT_INFO_LOG_BUFFER, JIT_ERROR_LOG_BUFFER, JIT_TARGET_FROM_CUCONTEXT, or JIT_TARGET.

This method is equivalent to invoking LinkAddData on the contents of the file.

Parameters:

state - a pending linker action

type - the type of the input data

path - path to the input file

options - options to be applied only for this input (overrides options from LinkCreate)

optionValues - array of option values, each cast to void *

ncuLinkComplete

public static int ncuLinkComplete(long state,
 long cubinOut,
 long sizeOut)

Unsafe version of: LinkComplete

cuLinkComplete

public static int cuLinkComplete(long state,
 PointerBuffer cubinOut,
 PointerBuffer sizeOut)

Complete a pending linker invocation.

Completes the pending linker action and returns the cubin image for the linked device code, which can be used with ModuleLoadData. The cubin is owned by state, so it should be loaded before state is destroyed via LinkDestroy. This call does not destroy state.

Parameters:

state - a pending linker invocation

cubinOut - on success, this will point to the output image

sizeOut - optional parameter to receive the size of the generated image

cuLinkDestroy

public static int cuLinkDestroy(long state)

Destroys state for a JIT linker invocation.

Parameters:

state - state object for the linker invocation

ncuMemGetInfo

public static int ncuMemGetInfo(long free,
 long total)

Unsafe version of: MemGetInfo

cuMemGetInfo

public static int cuMemGetInfo(PointerBuffer free,
 PointerBuffer total)

Gets free and total memory.

Returns in *total the total amount of memory available to the the current context. Returns in *free the amount of memory on the device that is free according to the OS. CUDA is not guaranteed to be able to allocate all of the memory that the OS reports as free.

Parameters:

free - returned free memory in bytes

total - returned total memory in bytes

ncuMemAlloc

public static int ncuMemAlloc(long dptr,
 long bytesize)

Unsafe version of: MemAlloc

cuMemAlloc

public static int cuMemAlloc(PointerBuffer dptr,
 long bytesize)

Allocates device memory.

Allocates bytesize bytes of linear memory on the device and returns in *dptr a pointer to the allocated memory. The allocated memory is suitably aligned for any kind of variable. The memory is not cleared. If bytesize is 0, cuMemAlloc() returns CUDA_ERROR_INVALID_VALUE.

Parameters:

dptr - returned device pointer

bytesize - requested allocation size in bytes

ncuMemAllocPitch

public static int ncuMemAllocPitch(long dptr,
 long pPitch,
 long WidthInBytes,
 long Height,
 int ElementSizeBytes)

Unsafe version of: MemAllocPitch

cuMemAllocPitch

public static int cuMemAllocPitch(PointerBuffer dptr,
 PointerBuffer pPitch,
 long WidthInBytes,
 long Height,
 int ElementSizeBytes)

Allocates pitched device memory.

Allocates at least WidthInBytes * Height bytes of linear memory on the device and returns in *dptr a pointer to the allocated memory. The function may pad the allocation to ensure that corresponding pointers in any given row will continue to meet the alignment requirements for coalescing as the address is updated from row to row. ElementSizeBytes specifies the size of the largest reads and writes that will be performed on the memory range. ElementSizeBytes may be 4, 8 or 16 (since coalesced memory transactions are not possible on other data sizes). If ElementSizeBytes is smaller than the actual read/write size of a kernel, the kernel will run correctly, but possibly at reduced speed. The pitch returned in *pPitch by cuMemAllocPitch() is the width in bytes of the allocation. The intended usage of pitch is as a separate parameter of the allocation, used to compute addresses within the 2D array. Given the row and column of an array element of type T, the address is computed as:

    T* pElement = (T*)((char*)BaseAddress + Row * Pitch) + Column;

The pitch returned by cuMemAllocPitch() is guaranteed to work with Memcpy2D under all circumstances. For allocations of 2D arrays, it is recommended that programmers consider performing pitch allocations using cuMemAllocPitch(). Due to alignment restrictions in the hardware, this is especially true if the application will be performing 2D memory copies between different regions of device memory (whether linear memory or CUDA arrays).

The byte alignment of the pitch returned by cuMemAllocPitch() is guaranteed to match or exceed the alignment requirement for texture binding with TexRefSetAddress2D.

Parameters:

dptr - returned device pointer

pPitch - returned pitch of allocation in bytes

WidthInBytes - requested allocation width in bytes

Height - requested allocation height in rows

ElementSizeBytes - size of largest reads/writes for range

cuMemFree

public static int cuMemFree(long dptr)

Frees device memory.

Frees the memory space pointed to by dptr, which must have been returned by a previous call to MemAlloc or MemAllocPitch.

Parameters:

dptr - pointer to memory to free

ncuMemGetAddressRange

public static int ncuMemGetAddressRange(long pbase,
 long psize,
 long dptr)

Unsafe version of: MemGetAddressRange

cuMemGetAddressRange

public static int cuMemGetAddressRange(@Nullable
 PointerBuffer pbase,
 @Nullable
 PointerBuffer psize,
 long dptr)

Get information on memory allocations.

Returns the base address in *pbase and size in *psize of the allocation by MemAlloc or MemAllocPitch that contains the input pointer dptr. Both parameters pbase and psize are optional. If one of them is NULL, it is ignored.

Parameters:

pbase - returned base address

psize - returned size of device memory allocation

dptr - device pointer to query

ncuMemAllocHost

public static int ncuMemAllocHost(long pp,
 long bytesize)

Unsafe version of: MemAllocHost

cuMemAllocHost

public static int cuMemAllocHost(PointerBuffer pp,
 long bytesize)

Allocates page-locked host memory.

Allocates bytesize bytes of host memory that is page-locked and accessible to the device. The driver tracks the virtual memory ranges allocated with this function and automatically accelerates calls to functions such as Memcpy. Since the memory can be accessed directly by the device, it can be read or written with much higher bandwidth than pageable memory obtained with functions such as malloc(). Allocating excessive amounts of memory with cuMemAllocHost() may degrade system performance, since it reduces the amount of memory available to the system for paging. As a result, this function is best used sparingly to allocate staging areas for data exchange between host and device.

Note all host memory allocated using cuMemHostAlloc() will automatically be immediately accessible to all contexts on all devices which support unified addressing (as may be queried using DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING). The device pointer that may be used to access this host memory from those contexts is always equal to the returned host pointer *pp. See CUDA_UNIFIED for additional details.

Parameters:

pp - returned host pointer to page-locked memory

bytesize - requested allocation size in bytes

ncuMemFreeHost

public static int ncuMemFreeHost(long p)

Unsafe version of: MemFreeHost

cuMemFreeHost

public static int cuMemFreeHost(ByteBuffer p)

Frees page-locked host memory.

Frees the memory space pointed to by p, which must have been returned by a previous call to MemAllocHost.

Parameters:

p - pointer to memory to free

ncuMemHostAlloc

public static int ncuMemHostAlloc(long pp,
 long bytesize,
 int Flags)

Unsafe version of: MemHostAlloc

cuMemHostAlloc

public static int cuMemHostAlloc(PointerBuffer pp,
 long bytesize,
 int Flags)

Allocates page-locked host memory.

Allocates bytesize bytes of host memory that is page-locked and accessible to the device. The driver tracks the virtual memory ranges allocated with this function and automatically accelerates calls to functions such as MemcpyHtoD. Since the memory can be accessed directly by the device, it can be read or written with much higher bandwidth than pageable memory obtained with functions such as malloc(). Allocating excessive amounts of pinned memory may degrade system performance, since it reduces the amount of memory available to the system for paging. As a result, this function is best used sparingly to allocate staging areas for data exchange between host and device.

The Flags parameter enables different options to be specified that affect the allocation, as follows:

• MEMHOSTALLOC_PORTABLE: The memory returned by this call will be considered as pinned memory by all CUDA contexts, not just the one that performed the allocation.
• MEMHOSTALLOC_DEVICEMAP: Maps the allocation into the CUDA address space. The device pointer to the memory may be obtained by calling MemHostGetDevicePointer.
• MEMHOSTALLOC_WRITECOMBINED: Allocates the memory as write-combined (WC). WC memory can be transferred across the PCI Express bus more quickly on some system configurations, but cannot be read efficiently by most CPUs. WC memory is a good option for buffers that will be written by the CPU and read by the GPU via mapped pinned memory or host->device transfers.

All of these flags are orthogonal to one another: a developer may allocate memory that is portable, mapped and/or write-combined with no restrictions.

The MEMHOSTALLOC_DEVICEMAP flag may be specified on CUDA contexts for devices that do not support mapped pinned memory. The failure is deferred to MemHostGetDevicePointer because the memory may be mapped into other CUDA contexts via the MEMHOSTALLOC_PORTABLE flag.

The memory allocated by this function must be freed with MemFreeHost.

Note all host memory allocated using cuMemHostAlloc() will automatically be immediately accessible to all contexts on all devices which support unified addressing (as may be queried using DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING). Unless the flag MEMHOSTALLOC_WRITECOMBINED is specified, the device pointer that may be used to access this host memory from those contexts is always equal to the returned host pointer *pp. If the flag MEMHOSTALLOC_WRITECOMBINED is specified, then the function MemHostGetDevicePointer must be used to query the device pointer, even if the context supports unified addressing. See CUDA_UNIFIED for additional details.

Parameters:

pp - returned host pointer to page-locked memory

bytesize - requested allocation size in bytes

Flags - flags for allocation request

ncuMemHostGetDevicePointer

public static int ncuMemHostGetDevicePointer(long pdptr,
 long p,
 int Flags)

Unsafe version of: MemHostGetDevicePointer

cuMemHostGetDevicePointer

public static int cuMemHostGetDevicePointer(PointerBuffer pdptr,
 ByteBuffer p,
 int Flags)

Passes back device pointer of mapped pinned memory.

Passes back the device pointer pdptr corresponding to the mapped, pinned host buffer p allocated by MemHostAlloc.

cuMemHostGetDevicePointer() will fail if the MEMHOSTALLOC_DEVICEMAP flag was not specified at the time the memory was allocated, or if the function is called on a GPU that does not support mapped pinned memory.

For devices that have a non-zero value for the device attribute DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM, the memory can also be accessed from the device using the host pointer p. The device pointer returned by cuMemHostGetDevicePointer() may or may not match the original host pointer p and depends on the devices visible to the application. If all devices visible to the application have a non-zero value for the device attribute, the device pointer returned by cuMemHostGetDevicePointer() will match the original pointer p. If any device visible to the application has a zero value for the device attribute, the device pointer returned by cuMemHostGetDevicePointer() will not match the original host pointer p, but it will be suitable for use on all devices provided Unified Virtual Addressing is enabled. In such systems, it is valid to access the memory using either pointer on devices that have a non-zero value for the device attribute. Note however that such devices should access the memory using only of the two pointers and not both.

Flags provides for future releases. For now, it must be set to 0.

Parameters:

pdptr - returned device pointer

p - host pointer

Flags - options (must be 0)

ncuMemHostGetFlags

public static int ncuMemHostGetFlags(long pFlags,
 long p)

Unsafe version of: MemHostGetFlags

cuMemHostGetFlags

public static int cuMemHostGetFlags(IntBuffer pFlags,
 ByteBuffer p)

Passes back flags that were used for a pinned allocation

Passes back the flags pFlags that were specified when allocating the pinned host buffer p allocated by MemHostAlloc.

cuMemHostGetFlags() will fail if the pointer does not reside in an allocation performed by MemAllocHost or cuMemHostAlloc().

Parameters:

pFlags - returned flags word

p - host pointer

ncuMemAllocManaged

public static int ncuMemAllocManaged(long dptr,
 long bytesize,
 int flags)

Unsafe version of: MemAllocManaged

cuMemAllocManaged

public static int cuMemAllocManaged(PointerBuffer dptr,
 long bytesize,
 int flags)

Allocates memory that will be automatically managed by the Unified Memory system.

Allocates bytesize bytes of managed memory on the device and returns in *dptr a pointer to the allocated memory. If the device doesn't support allocating managed memory, CUDA_ERROR_NOT_SUPPORTED is returned. Support for managed memory can be queried using the device attribute DEVICE_ATTRIBUTE_MANAGED_MEMORY. The allocated memory is suitably aligned for any kind of variable. The memory is not cleared. If bytesize is 0, MemAllocManaged returns CUDA_ERROR_INVALID_VALUE. The pointer is valid on the CPU and on all GPUs in the system that support managed memory. All accesses to this pointer must obey the Unified Memory programming model.

flags specifies the default stream association for this allocation. flags must be one of MEM_ATTACH_GLOBAL or MEM_ATTACH_HOST. If MEM_ATTACH_GLOBAL is specified, then this memory is accessible from any stream on any device. If MEM_ATTACH_HOST is specified, then the allocation should not be accessed from devices that have a zero value for the device attribute DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS; an explicit call to StreamAttachMemAsync will be required to enable access on such devices.

If the association is later changed via StreamAttachMemAsync to a single stream, the default association as specifed during MemAllocManaged is restored when that stream is destroyed. For __managed__ variables, the default association is always MEM_ATTACH_GLOBAL. Note that destroying a stream is an asynchronous operation, and as a result, the change to default association won't happen until all work in the stream has completed.

Memory allocated with MemAllocManaged should be released with MemFree.

Device memory oversubscription is possible for GPUs that have a non-zero value for the device attribute DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS. Managed memory on such GPUs may be evicted from device memory to host memory at any time by the Unified Memory driver in order to make room for other allocations.

In a multi-GPU system where all GPUs have a non-zero value for the device attribute DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS, managed memory may not be populated when this API returns and instead may be populated on access. In such systems, managed memory can migrate to any processor's memory at any time. The Unified Memory driver will employ heuristics to maintain data locality and prevent excessive page faults to the extent possible. The application can also guide the driver about memory usage patterns via MemAdvise. The application can also explicitly migrate memory to a desired processor's memory via MemPrefetchAsync.

In a multi-GPU system where all of the GPUs have a zero value for the device attribute DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS and all the GPUs have peer-to-peer support with each other, the physical storage for managed memory is created on the GPU which is active at the time MemAllocManaged is called. All other GPUs will reference the data at reduced bandwidth via peer mappings over the PCIe bus. The Unified Memory driver does not migrate memory among such GPUs.

In a multi-GPU system where not all GPUs have peer-to-peer support with each other and where the value of the device attribute DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS is zero for at least one of those GPUs, the location chosen for physical storage of managed memory is system-dependent.

• On Linux, the location chosen will be device memory as long as the current set of active contexts are on devices that either have peer-to-peer support with each other or have a non-zero value for the device attribute DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS. If there is an active context on a GPU that does not have a non-zero value for that device attribute and it does not have peer-to-peer support with the other devices that have active contexts on them, then the location for physical storage will be 'zero-copy' or host memory. Note that this means that managed memory that is located in device memory is migrated to host memory if a new context is created on a GPU that doesn't have a non-zero value for the device attribute and does not support peer-to-peer with at least one of the other devices that has an active context. This in turn implies that context creation may fail if there is insufficient host memory to migrate all managed allocations.
• On Windows, the physical storage is always created in 'zero-copy' or host memory. All GPUs will reference the data at reduced bandwidth over the PCIe bus. In these circumstances, use of the environment variable CUDA_VISIBLE_DEVICES is recommended to restrict CUDA to only use those GPUs that have peer-to-peer support. Alternatively, users can also set CUDA_MANAGED_FORCE_DEVICE_ALLOC to a non-zero value to force the driver to always use device memory for physical storage. When this environment variable is set to a non-zero value, all contexts created in that process on devices that support managed memory have to be peer-to-peer compatible with each other. Context creation will fail if a context is created on a device that supports managed memory and is not peer-to-peer compatible with any of the other managed memory supporting devices on which contexts were previously created, even if those contexts have been destroyed. These environment variables are described in the CUDA programming guide under the "CUDA environment variables" section.
• On ARM, managed memory is not available on discrete gpu with Drive PX-2.

Parameters:

dptr - returned device pointer

bytesize - requested allocation size in bytes

flags - must be one of MEM_ATTACH_GLOBAL or MEM_ATTACH_HOST

ncuDeviceGetByPCIBusId

public static int ncuDeviceGetByPCIBusId(long dev,
 long pciBusId)

Unsafe version of: DeviceGetByPCIBusId

cuDeviceGetByPCIBusId

public static int cuDeviceGetByPCIBusId(IntBuffer dev,
 ByteBuffer pciBusId)

Returns a handle to a compute device.

Returns in *device a device handle given a PCI bus ID string.

Parameters:

dev - returned device handle

pciBusId - string in one of the following forms: [domain]:[bus]:[device].[function] [domain]:[bus]:[device] [bus]:[device].[function] where domain, bus, device, and function are all hexadecimal values

cuDeviceGetByPCIBusId

public static int cuDeviceGetByPCIBusId(IntBuffer dev,
 CharSequence pciBusId)

Returns a handle to a compute device.

Returns in *device a device handle given a PCI bus ID string.

Parameters:

dev - returned device handle

pciBusId - string in one of the following forms: [domain]:[bus]:[device].[function] [domain]:[bus]:[device] [bus]:[device].[function] where domain, bus, device, and function are all hexadecimal values

ncuDeviceGetPCIBusId

public static int ncuDeviceGetPCIBusId(long pciBusId,
 int len,
 int dev)

Unsafe version of: DeviceGetPCIBusId

Parameters:

len - maximum length of string to store in name

cuDeviceGetPCIBusId

public static int cuDeviceGetPCIBusId(ByteBuffer pciBusId,
 int dev)

Returns a PCI Bus Id string for the device.

Returns an ASCII string identifying the device dev in the NULL-terminated string pointed to by pciBusId. len specifies the maximum length of the string that may be returned.

Parameters:

pciBusId - returned identifier string for the device in the following format [domain]:[bus]:[device].[function] where domain, bus, device, and function are all hexadecimal values. pciBusId should be large enough to store 13 characters including the NULL-terminator.

dev - device to get identifier string for

ncuIpcGetEventHandle

public static int ncuIpcGetEventHandle(long pHandle,
 long event)

Unsafe version of: IpcGetEventHandle

cuIpcGetEventHandle

public static int cuIpcGetEventHandle(CUIPCEventHandle pHandle,
 long event)

Gets an interprocess handle for a previously allocated event.

Takes as input a previously allocated event. This event must have been created with the EVENT_INTERPROCESS and EVENT_DISABLE_TIMING flags set. This opaque handle may be copied into other processes and opened with IpcOpenEventHandle to allow efficient hardware synchronization between GPU work in different processes.

After the event has been opened in the importing process, EventRecord, EventSynchronize, StreamWaitEvent and EventQuery may be used in either process. Performing operations on the imported event after the exported event has been freed with EventDestroy will result in undefined behavior.

IPC functionality is restricted to devices with support for unified addressing on Linux and Windows operating systems. IPC functionality on Windows is restricted to GPUs in TCC mode.

Parameters:

pHandle - pointer to a user allocated CUipcEventHandle in which to return the opaque event handle

event - event allocated with EVENT_INTERPROCESS and EVENT_DISABLE_TIMING flags

ncuIpcOpenEventHandle

public static int ncuIpcOpenEventHandle(long phEvent,
 long handle)

Unsafe version of: IpcOpenEventHandle

cuIpcOpenEventHandle

public static int cuIpcOpenEventHandle(PointerBuffer phEvent,
 CUIPCEventHandle handle)

Opens an interprocess event handle for use in the current process.

Opens an interprocess event handle exported from another process with IpcGetEventHandle. This function returns a CUevent that behaves like a locally created event with the EVENT_DISABLE_TIMING flag specified. This event must be freed with EventDestroy.

Performing operations on the imported event after the exported event has been freed with cuEventDestroy will result in undefined behavior.

IPC functionality is restricted to devices with support for unified addressing on Linux and Windows operating systems. IPC functionality on Windows is restricted to GPUs in TCC mode.

Parameters:

phEvent - returns the imported event

handle - interprocess handle to open

ncuIpcGetMemHandle

public static int ncuIpcGetMemHandle(long pHandle,
 long dptr)

Unsafe version of: IpcGetMemHandle

cuIpcGetMemHandle

public static int cuIpcGetMemHandle(CUIPCMemHandle pHandle,
 long dptr)

Gets an interprocess memory handle for an existing device memory allocation.

Takes a pointer to the base of an existing device memory allocation created with MemAlloc and exports it for use in another process. This is a lightweight operation and may be called multiple times on an allocation without adverse effects.

If a region of memory is freed with MemFree and a subsequent call to MemAlloc returns memory with the same device address, IpcGetMemHandle will return a unique handle for the new memory.

IPC functionality is restricted to devices with support for unified addressing on Linux and Windows operating systems. IPC functionality on Windows is restricted to GPUs in TCC mode.

Parameters:

pHandle - pointer to user allocated CUipcMemHandle to return the handle in

dptr - base pointer to previously allocated device memory

ncuIpcOpenMemHandle

public static int ncuIpcOpenMemHandle(long pdptr,
 long handle,
 int Flags)

Unsafe version of: IpcOpenMemHandle

cuIpcOpenMemHandle

public static int cuIpcOpenMemHandle(PointerBuffer pdptr,
 CUIPCMemHandle handle,
 int Flags)

Opens an interprocess memory handle exported from another process and returns a device pointer usable in the local process.

Maps memory exported from another process with IpcGetMemHandle into the current device address space. For contexts on different devices cuIpcOpenMemHandle can attempt to enable peer access between the devices as if the user called CtxEnablePeerAccess. This behavior is controlled by the IPC_MEM_LAZY_ENABLE_PEER_ACCESS flag. DeviceCanAccessPeer can determine if a mapping is possible.

Contexts that may open CUIPCMemHandle are restricted in the following way. CUipcMemHandles from each CUdevice in a given process may only be opened by one CUcontext per CUdevice per other process.

If the memory handle has already been opened by the current context, the reference count on the handle is incremented by 1 and the existing device pointer is returned.

Memory returned from cuIpcOpenMemHandle must be freed with IpcCloseMemHandle.

Calling MemFree on an exported memory region before calling cuIpcCloseMemHandle in the importing context will result in undefined behavior.

IPC functionality is restricted to devices with support for unified addressing on Linux and Windows operating systems. IPC functionality on Windows is restricted to GPUs in TCC mode.

Note

No guarantees are made about the address returned in *pdptr. In particular, multiple processes may not receive the same address for the same handle.

Parameters:

pdptr - returned device pointer

handle - CUipcMemHandle to open

Flags - flags for this operation. Must be specified as IPC_MEM_LAZY_ENABLE_PEER_ACCESS.

cuIpcCloseMemHandle

public static int cuIpcCloseMemHandle(long dptr)

Attempts to close memory mapped with IpcOpenMemHandle.

Decrements the reference count of the memory returned by cuIpcOpenMemHandle() by 1. When the reference count reaches 0, this API unmaps the memory. The original allocation in the exporting process as well as imported mappings in other processes will be unaffected.

Any resources used to enable peer access will be freed if this is the last mapping using them.

IPC functionality is restricted to devices with support for unified addressing on Linux and Windows operating systems. IPC functionality on Windows is restricted to GPUs in TCC mode

Parameters:

dptr - device pointer returned by cuIpcOpenMemHandle()

ncuMemHostRegister

public static int ncuMemHostRegister(long p,
 long bytesize,
 int Flags)

Unsafe version of: MemHostRegister

Parameters:

bytesize - size in bytes of the address range to page-lock

cuMemHostRegister

public static int cuMemHostRegister(ByteBuffer p,
 int Flags)

Registers an existing host memory range for use by CUDA.

Page-locks the memory range specified by p and bytesize and maps it for the device(s) as specified by Flags. This memory range also is added to the same tracking mechanism as MemHostAlloc to automatically accelerate calls to functions such as MemcpyHtoD. Since the memory can be accessed directly by the device, it can be read or written with much higher bandwidth than pageable memory that has not been registered. Page-locking excessive amounts of memory may degrade system performance, since it reduces the amount of memory available to the system for paging. As a result, this function is best used sparingly to register staging areas for data exchange between host and device.

This function has limited support on Mac OS X. OS 10.7 or higher is required.

All flags are orthogonal to one another: a developer may page-lock memory that is portable or mapped with no restrictions.

The MEMHOSTREGISTER_DEVICEMAP flag may be specified on CUDA contexts for devices that do not support mapped pinned memory. The failure is deferred to MemHostGetDevicePointer because the memory may be mapped into other CUDA contexts via the MEMHOSTREGISTER_PORTABLE flag.

For devices that have a non-zero value for the device attribute DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM, the memory can also be accessed from the device using the host pointer p. The device pointer returned by cuMemHostGetDevicePointer() may or may not match the original host pointer ptr and depends on the devices visible to the application. If all devices visible to the application have a non-zero value for the device attribute, the device pointer returned by cuMemHostGetDevicePointer() will match the original pointer ptr. If any device visible to the application has a zero value for the device attribute, the device pointer returned by cuMemHostGetDevicePointer() will not match the original host pointer ptr, but it will be suitable for use on all devices provided Unified Virtual Addressing is enabled. In such systems, it is valid to access the memory using either pointer on devices that have a non-zero value for the device attribute. Note however that such devices should access the memory using only of the two pointers and not both.

The memory page-locked by this function must be unregistered with MemHostUnregister.

Parameters:

p - host pointer to memory to page-lock

Flags - flags for allocation request. One or more of:

MEMHOSTREGISTER_PORTABLE	MEMHOSTREGISTER_DEVICEMAP	MEMHOSTREGISTER_IOMEMORY
MEMHOSTREGISTER_READ_ONLY

ncuMemHostUnregister

public static int ncuMemHostUnregister(long p)

Unsafe version of: MemHostUnregister

cuMemHostUnregister

public static int cuMemHostUnregister(ByteBuffer p)

Unregisters a memory range that was registered with MemHostRegister.

Unmaps the memory range whose base address is specified by p, and makes it pageable again.

The base address must be the same one specified to MemHostRegister.

Parameters:

p - host pointer to memory to unregister

cuMemcpy

public static int cuMemcpy(long dst,
 long src,
 long ByteCount)

Copies memory.

Copies data between two pointers. dst and src are base pointers of the destination and source, respectively. ByteCount specifies the number of bytes to copy. Note that this function infers the type of the transfer (host to host, host to device, device to device, or device to host) from the pointer values. This function is only allowed in contexts which support unified addressing.

Parameters:

dst - destination unified virtual address space pointer

src - source unified virtual address space pointer

ByteCount - size of memory copy in bytes

cuMemcpyPeer

public static int cuMemcpyPeer(long dstDevice,
 long dstContext,
 long srcDevice,
 long srcContext,
 long ByteCount)

Copies device memory between two contexts.

Copies from device memory in one context to device memory in another context. dstDevice is the base device pointer of the destination memory and dstContext is the destination context. srcDevice is the base device pointer of the source memory and srcContext is the source pointer. ByteCount specifies the number of bytes to copy.

Parameters:

dstDevice - destination device pointer

dstContext - destination context

srcDevice - source device pointer

srcContext - source context

ByteCount - size of memory copy in bytes

ncuMemcpyHtoD

public static int ncuMemcpyHtoD(long dstDevice,
 long srcHost,
 long ByteCount)

Unsafe version of: MemcpyHtoD

Parameters:

ByteCount - size of memory copy in bytes

cuMemcpyHtoD

public static int cuMemcpyHtoD(long dstDevice,
 ByteBuffer srcHost)

Copies memory from Host to Device.

Copies from host memory to device memory. dstDevice and srcHost are the base addresses of the destination and source, respectively. ByteCount specifies the number of bytes to copy.

Parameters:

dstDevice - destination device pointer

srcHost - source host pointer

cuMemcpyHtoD

public static int cuMemcpyHtoD(long dstDevice,
 ShortBuffer srcHost)

Copies memory from Host to Device.

Copies from host memory to device memory. dstDevice and srcHost are the base addresses of the destination and source, respectively. ByteCount specifies the number of bytes to copy.

Parameters:

dstDevice - destination device pointer

srcHost - source host pointer

cuMemcpyHtoD

public static int cuMemcpyHtoD(long dstDevice,
 IntBuffer srcHost)

Copies memory from Host to Device.

Copies from host memory to device memory. dstDevice and srcHost are the base addresses of the destination and source, respectively. ByteCount specifies the number of bytes to copy.

Parameters:

dstDevice - destination device pointer

srcHost - source host pointer

cuMemcpyHtoD

public static int cuMemcpyHtoD(long dstDevice,
 LongBuffer srcHost)

Copies memory from Host to Device.

Copies from host memory to device memory. dstDevice and srcHost are the base addresses of the destination and source, respectively. ByteCount specifies the number of bytes to copy.

Parameters:

dstDevice - destination device pointer

srcHost - source host pointer

cuMemcpyHtoD

public static int cuMemcpyHtoD(long dstDevice,
 FloatBuffer srcHost)

Copies memory from Host to Device.

Copies from host memory to device memory. dstDevice and srcHost are the base addresses of the destination and source, respectively. ByteCount specifies the number of bytes to copy.

Parameters:

dstDevice - destination device pointer

srcHost - source host pointer

cuMemcpyHtoD

public static int cuMemcpyHtoD(long dstDevice,
 DoubleBuffer srcHost)

Copies memory from Host to Device.

Copies from host memory to device memory. dstDevice and srcHost are the base addresses of the destination and source, respectively. ByteCount specifies the number of bytes to copy.

Parameters:

dstDevice - destination device pointer

srcHost - source host pointer

cuMemcpyHtoD

public static int cuMemcpyHtoD(long dstDevice,
 PointerBuffer srcHost)

Copies memory from Host to Device.

Copies from host memory to device memory. dstDevice and srcHost are the base addresses of the destination and source, respectively. ByteCount specifies the number of bytes to copy.

Parameters:

dstDevice - destination device pointer

srcHost - source host pointer

ncuMemcpyDtoH

public static int ncuMemcpyDtoH(long dstHost,
 long srcDevice,
 long ByteCount)

Unsafe version of: MemcpyDtoH

Parameters:

ByteCount - size of memory copy in bytes

cuMemcpyDtoH

public static int cuMemcpyDtoH(ByteBuffer dstHost,
 long srcDevice)

Copies memory from Device to Host.

Copies from device to host memory. dstHost and srcDevice specify the base pointers of the destination and source, respectively. ByteCount specifies the number of bytes to copy.

Parameters:

dstHost - destination host pointer

srcDevice - source device pointer

cuMemcpyDtoH

public static int cuMemcpyDtoH(ShortBuffer dstHost,
 long srcDevice)

Copies memory from Device to Host.

Copies from device to host memory. dstHost and srcDevice specify the base pointers of the destination and source, respectively. ByteCount specifies the number of bytes to copy.

Parameters:

dstHost - destination host pointer

srcDevice - source device pointer

cuMemcpyDtoH

public static int cuMemcpyDtoH(IntBuffer dstHost,
 long srcDevice)

Copies memory from Device to Host.

Copies from device to host memory. dstHost and srcDevice specify the base pointers of the destination and source, respectively. ByteCount specifies the number of bytes to copy.

Parameters:

dstHost - destination host pointer

srcDevice - source device pointer

cuMemcpyDtoH

public static int cuMemcpyDtoH(LongBuffer dstHost,
 long srcDevice)

Copies memory from Device to Host.

Copies from device to host memory. dstHost and srcDevice specify the base pointers of the destination and source, respectively. ByteCount specifies the number of bytes to copy.

Parameters:

dstHost - destination host pointer

srcDevice - source device pointer

cuMemcpyDtoH

public static int cuMemcpyDtoH(FloatBuffer dstHost,
 long srcDevice)

Copies memory from Device to Host.

Copies from device to host memory. dstHost and srcDevice specify the base pointers of the destination and source, respectively. ByteCount specifies the number of bytes to copy.

Parameters:

dstHost - destination host pointer

srcDevice - source device pointer

cuMemcpyDtoH

public static int cuMemcpyDtoH(DoubleBuffer dstHost,
 long srcDevice)

Copies memory from Device to Host.

Copies from device to host memory. dstHost and srcDevice specify the base pointers of the destination and source, respectively. ByteCount specifies the number of bytes to copy.

Parameters:

dstHost - destination host pointer

srcDevice - source device pointer

cuMemcpyDtoH

public static int cuMemcpyDtoH(PointerBuffer dstHost,
 long srcDevice)

Copies memory from Device to Host.

Copies from device to host memory. dstHost and srcDevice specify the base pointers of the destination and source, respectively. ByteCount specifies the number of bytes to copy.

Parameters:

dstHost - destination host pointer

srcDevice - source device pointer

cuMemcpyDtoD

public static int cuMemcpyDtoD(long dstDevice,
 long srcDevice,
 long ByteCount)

Copies memory from Device to Device.

Copies from device memory to device memory. dstDevice and srcDevice are the base pointers of the destination and source, respectively. ByteCount specifies the number of bytes to copy.

Parameters:

dstDevice - destination device pointer

srcDevice - source device pointer

ByteCount - size of memory copy in bytes

cuMemcpyDtoA

public static int cuMemcpyDtoA(long dstArray,
 long dstOffset,
 long srcDevice,
 long ByteCount)

Copies memory from Device to Array.

Copies from device memory to a 1D CUDA array. dstArray and dstOffset specify the CUDA array handle and starting index of the destination data. srcDevice specifies the base pointer of the source. ByteCount specifies the number of bytes to copy.

Parameters:

dstArray - destination array

dstOffset - offset in bytes of destination array

srcDevice - source device pointer

ByteCount - size of memory copy in bytes

cuMemcpyAtoD

public static int cuMemcpyAtoD(long dstDevice,
 long srcArray,
 long srcOffset,
 long ByteCount)

Copies memory from Array to Device.

Copies from one 1D CUDA array to device memory. dstDevice specifies the base pointer of the destination and must be naturally aligned with the CUDA array elements. srcArray and srcOffset specify the CUDA array handle and the offset in bytes into the array where the copy is to begin. ByteCount specifies the number of bytes to copy and must be evenly divisible by the array element size.

Parameters:

dstDevice - destination device pointer

srcArray - source array

srcOffset - offset in bytes of source array

ByteCount - size of memory copy in bytes

ncuMemcpyHtoA

public static int ncuMemcpyHtoA(long dstArray,
 long dstOffset,
 long srcHost,
 long ByteCount)

Unsafe version of: MemcpyHtoA

Parameters:

ByteCount - size of memory copy in bytes

cuMemcpyHtoA

public static int cuMemcpyHtoA(long dstArray,
 long dstOffset,
 ByteBuffer srcHost)

Copies memory from Host to Array.

Copies from host memory to a 1D CUDA array. dstArray and dstOffset specify the CUDA array handle and starting offset in bytes of the destination data. pSrc specifies the base address of the source. ByteCount specifies the number of bytes to copy.

Parameters:

dstArray - destination array

dstOffset - offset in bytes of destination array

srcHost - source host pointer

cuMemcpyHtoA

public static int cuMemcpyHtoA(long dstArray,
 long dstOffset,
 ShortBuffer srcHost)

Copies memory from Host to Array.

Copies from host memory to a 1D CUDA array. dstArray and dstOffset specify the CUDA array handle and starting offset in bytes of the destination data. pSrc specifies the base address of the source. ByteCount specifies the number of bytes to copy.

Parameters:

dstArray - destination array

dstOffset - offset in bytes of destination array

srcHost - source host pointer

cuMemcpyHtoA

public static int cuMemcpyHtoA(long dstArray,
 long dstOffset,
 IntBuffer srcHost)

Copies memory from Host to Array.

Copies from host memory to a 1D CUDA array. dstArray and dstOffset specify the CUDA array handle and starting offset in bytes of the destination data. pSrc specifies the base address of the source. ByteCount specifies the number of bytes to copy.

Parameters:

dstArray - destination array

dstOffset - offset in bytes of destination array

srcHost - source host pointer

cuMemcpyHtoA

public static int cuMemcpyHtoA(long dstArray,
 long dstOffset,
 LongBuffer srcHost)

Copies memory from Host to Array.

Copies from host memory to a 1D CUDA array. dstArray and dstOffset specify the CUDA array handle and starting offset in bytes of the destination data. pSrc specifies the base address of the source. ByteCount specifies the number of bytes to copy.

Parameters:

dstArray - destination array

dstOffset - offset in bytes of destination array

srcHost - source host pointer

cuMemcpyHtoA

public static int cuMemcpyHtoA(long dstArray,
 long dstOffset,
 FloatBuffer srcHost)

Copies memory from Host to Array.

Copies from host memory to a 1D CUDA array. dstArray and dstOffset specify the CUDA array handle and starting offset in bytes of the destination data. pSrc specifies the base address of the source. ByteCount specifies the number of bytes to copy.

Parameters:

dstArray - destination array

dstOffset - offset in bytes of destination array

srcHost - source host pointer

cuMemcpyHtoA

public static int cuMemcpyHtoA(long dstArray,
 long dstOffset,
 DoubleBuffer srcHost)

Copies memory from Host to Array.

Copies from host memory to a 1D CUDA array. dstArray and dstOffset specify the CUDA array handle and starting offset in bytes of the destination data. pSrc specifies the base address of the source. ByteCount specifies the number of bytes to copy.

Parameters:

dstArray - destination array

dstOffset - offset in bytes of destination array

srcHost - source host pointer

cuMemcpyHtoA

public static int cuMemcpyHtoA(long dstArray,
 long dstOffset,
 PointerBuffer srcHost)

Copies memory from Host to Array.

Copies from host memory to a 1D CUDA array. dstArray and dstOffset specify the CUDA array handle and starting offset in bytes of the destination data. pSrc specifies the base address of the source. ByteCount specifies the number of bytes to copy.

Parameters:

dstArray - destination array

dstOffset - offset in bytes of destination array

srcHost - source host pointer

ncuMemcpyAtoH

public static int ncuMemcpyAtoH(long dstHost,
 long srcArray,
 long srcOffset,
 long ByteCount)

Unsafe version of: MemcpyAtoH

Parameters:

ByteCount - size of memory copy in bytes

cuMemcpyAtoH

public static int cuMemcpyAtoH(ByteBuffer dstHost,
 long srcArray,
 long srcOffset)

Copies memory from Array to Host.

Copies from one 1D CUDA array to host memory. dstHost specifies the base pointer of the destination. srcArray and srcOffset specify the CUDA array handle and starting offset in bytes of the source data. ByteCount specifies the number of bytes to copy.

Parameters:

dstHost - destination device pointer

srcArray - source array

srcOffset - offset in bytes of source array

cuMemcpyAtoH

public static int cuMemcpyAtoH(ShortBuffer dstHost,
 long srcArray,
 long srcOffset)

Copies memory from Array to Host.

Copies from one 1D CUDA array to host memory. dstHost specifies the base pointer of the destination. srcArray and srcOffset specify the CUDA array handle and starting offset in bytes of the source data. ByteCount specifies the number of bytes to copy.

Parameters:

dstHost - destination device pointer

srcArray - source array

srcOffset - offset in bytes of source array

cuMemcpyAtoH

public static int cuMemcpyAtoH(IntBuffer dstHost,
 long srcArray,
 long srcOffset)

Copies memory from Array to Host.

Copies from one 1D CUDA array to host memory. dstHost specifies the base pointer of the destination. srcArray and srcOffset specify the CUDA array handle and starting offset in bytes of the source data. ByteCount specifies the number of bytes to copy.

Parameters:

dstHost - destination device pointer

srcArray - source array

srcOffset - offset in bytes of source array

cuMemcpyAtoH

public static int cuMemcpyAtoH(LongBuffer dstHost,
 long srcArray,
 long srcOffset)

Copies memory from Array to Host.

Copies from one 1D CUDA array to host memory. dstHost specifies the base pointer of the destination. srcArray and srcOffset specify the CUDA array handle and starting offset in bytes of the source data. ByteCount specifies the number of bytes to copy.

Parameters:

dstHost - destination device pointer

srcArray - source array

srcOffset - offset in bytes of source array

cuMemcpyAtoH

public static int cuMemcpyAtoH(FloatBuffer dstHost,
 long srcArray,
 long srcOffset)

Copies memory from Array to Host.

Copies from one 1D CUDA array to host memory. dstHost specifies the base pointer of the destination. srcArray and srcOffset specify the CUDA array handle and starting offset in bytes of the source data. ByteCount specifies the number of bytes to copy.

Parameters:

dstHost - destination device pointer

srcArray - source array

srcOffset - offset in bytes of source array

cuMemcpyAtoH

public static int cuMemcpyAtoH(DoubleBuffer dstHost,
 long srcArray,
 long srcOffset)

Copies memory from Array to Host.

Copies from one 1D CUDA array to host memory. dstHost specifies the base pointer of the destination. srcArray and srcOffset specify the CUDA array handle and starting offset in bytes of the source data. ByteCount specifies the number of bytes to copy.

Parameters:

dstHost - destination device pointer

srcArray - source array

srcOffset - offset in bytes of source array

cuMemcpyAtoH

public static int cuMemcpyAtoH(PointerBuffer dstHost,
 long srcArray,
 long srcOffset)

Copies memory from Array to Host.

Copies from one 1D CUDA array to host memory. dstHost specifies the base pointer of the destination. srcArray and srcOffset specify the CUDA array handle and starting offset in bytes of the source data. ByteCount specifies the number of bytes to copy.

Parameters:

dstHost - destination device pointer

srcArray - source array

srcOffset - offset in bytes of source array

cuMemcpyAtoA

public static int cuMemcpyAtoA(long dstArray,
 long dstOffset,
 long srcArray,
 long srcOffset,
 long ByteCount)

Copies memory from Array to Array.

Copies from one 1D CUDA array to another. dstArray and srcArray specify the handles of the destination and source CUDA arrays for the copy, respectively. dstOffset and srcOffset specify the destination and source offsets in bytes into the CUDA arrays. ByteCount is the number of bytes to be copied. The size of the elements in the CUDA arrays need not be the same format, but the elements must be the same size; and count must be evenly divisible by that size.

Parameters:

dstArray - destination array

dstOffset - offset in bytes of destination array

srcArray - source array

srcOffset - offset in bytes of source array

ByteCount - size of memory copy in bytes

ncuMemcpy2D

public static int ncuMemcpy2D(long pCopy)

Unsafe version of: Memcpy2D

cuMemcpy2D

public static int cuMemcpy2D(CUDA_MEMCPY2D pCopy)

Copies memory for 2D arrays.

Perform a 2D memory copy according to the parameters specified in pCopy.

If srcMemoryType is MEMORYTYPE_UNIFIED, srcDevice and srcPitch specify the (unified virtual address space) base address of the source data and the bytes per row to apply. srcArray is ignored. This value may be used only if unified addressing is supported in the calling context.

If srcMemoryType is MEMORYTYPE_HOST, srcHost and srcPitch specify the (host) base address of the source data and the bytes per row to apply. srcArray is ignored.

If srcMemoryType is MEMORYTYPE_DEVICE, srcDevice and srcPitch specify the (device) base address of the source data and the bytes per row to apply. srcArray is ignored.

If srcMemoryType is MEMORYTYPE_ARRAY, srcArray specifies the handle of the source data. srcHost, srcDevice and srcPitch are ignored.

If dstMemoryType is MEMORYTYPE_HOST, dstHost and dstPitch specify the (host) base address of the destination data and the bytes per row to apply. dstArray is ignored.

If dstMemoryType is MEMORYTYPE_UNIFIED, dstDevice and dstPitch specify the (unified virtual address space) base address of the source data and the bytes per row to apply. dstArray is ignored. This value may be used only if unified addressing is supported in the calling context.

If dstMemoryType is MEMORYTYPE_DEVICE, dstDevice and dstPitch specify the (device) base address of the destination data and the bytes per row to apply. dstArray is ignored.

If dstMemoryType is MEMORYTYPE_ARRAY, dstArray specifies the handle of the destination data. dstHost, dstDevice and dstPitch are ignored.

srcXInBytes and srcY specify the base address of the source data for the copy.

For host pointers, the starting address is

 voidStart = (void*)((char*)srcHost+srcY*srcPitch + srcXInBytes);

For device pointers, the starting address is

 CUdeviceptr Start = srcDevice+srcY*srcPitch+srcXInBytes;

For CUDA arrays, srcXInBytes must be evenly divisible by the array element size.

dstXInBytes and dstY specify the base address of the destination data for the copy.

For host pointers, the base address is

 voiddstStart = (void*)((char*)dstHost+dstY*dstPitch + dstXInBytes);

For device pointers, the starting address is

 CUdeviceptr dstStart = dstDevice+dstY*dstPitch+dstXInBytes;

For CUDA arrays, dstXInBytes must be evenly divisible by the array element size.

WidthInBytes and Height specify the width (in bytes) and height of the 2D copy being performed.

If specified, srcPitch must be greater than or equal to WidthInBytes + srcXInBytes, and dstPitch must be greater than or equal to WidthInBytes + dstXInBytes.

cuMemcpy2D() returns an error if any pitch is greater than the maximum allowed (DEVICE_ATTRIBUTE_MAX_PITCH). cuMemAllocPitch() passes back pitches that always work with cuMemcpy2D(). On intra-device memory copies (device to device, CUDA array to device, CUDA array to CUDA array), cuMemcpy2D() may fail for pitches not computed by MemAllocPitch. Memcpy2DUnaligned does not have this restriction, but may run significantly slower in the cases where cuMemcpy2D() would have returned an error code.

Parameters:

pCopy - parameters for the memory copy

ncuMemcpy2DUnaligned

public static int ncuMemcpy2DUnaligned(long pCopy)

Unsafe version of: Memcpy2DUnaligned

cuMemcpy2DUnaligned

public static int cuMemcpy2DUnaligned(CUDA_MEMCPY2D pCopy)

Copies memory for 2D arrays.

Perform a 2D memory copy according to the parameters specified in pCopy.

If srcMemoryType is MEMORYTYPE_UNIFIED, srcDevice and srcPitch specify the (unified virtual address space) base address of the source data and the bytes per row to apply. srcArray is ignored. This value may be used only if unified addressing is supported in the calling context.

If srcMemoryType is MEMORYTYPE_HOST, srcHost and srcPitch specify the (host) base address of the source data and the bytes per row to apply. srcArray is ignored.

If srcMemoryType is MEMORYTYPE_DEVICE, srcDevice and srcPitch specify the (device) base address of the source data and the bytes per row to apply. srcArray is ignored.

If srcMemoryType is MEMORYTYPE_ARRAY, srcArray specifies the handle of the source data. srcHost, srcDevice and srcPitch are ignored.

If dstMemoryType is MEMORYTYPE_UNIFIED, dstDevice and dstPitch specify the (unified virtual address space) base address of the source data and the bytes per row to apply. dstArray is ignored. This value may be used only if unified addressing is supported in the calling context.

If dstMemoryType is MEMORYTYPE_HOST, dstHost and dstPitch specify the (host) base address of the destination data and the bytes per row to apply. dstArray is ignored.

If dstMemoryType is MEMORYTYPE_DEVICE, dstDevice and dstPitch specify the (device) base address of the destination data and the bytes per row to apply. dstArray is ignored.

If dstMemoryType is MEMORYTYPE_ARRAY, dstArray specifies the handle of the destination data. dstHost, dstDevice and dstPitch are ignored.

srcXInBytes and srcY specify the base address of the source data for the copy.

For host pointers, the starting address is

   void* Start = (void*)((char*)srcHost+srcY*srcPitch + srcXInBytes);

For device pointers, the starting address is

   CUdeviceptr Start = srcDevice+srcY*srcPitch+srcXInBytes;

For CUDA arrays, srcXInBytes must be evenly divisible by the array element size.

dstXInBytes and dstY specify the base address of the destination data for the copy.

For host pointers, the base address is

   void* dstStart = (void*)((char*)dstHost+dstY*dstPitch + dstXInBytes);

For device pointers, the starting address is

   CUdeviceptr dstStart = dstDevice+dstY*dstPitch+dstXInBytes;

For CUDA arrays, dstXInBytes must be evenly divisible by the array element size.

WidthInBytes and Height specify the width (in bytes) and height of the 2D copy being performed.

If specified, srcPitch must be greater than or equal to WidthInBytes + srcXInBytes, and dstPitch must be greater than or equal to WidthInBytes + dstXInBytes.

Memcpy2D returns an error if any pitch is greater than the maximum allowed (DEVICE_ATTRIBUTE_MAX_PITCH). MemAllocPitch passes back pitches that always work with cuMemcpy2D(). On intra-device memory copies (device to device, CUDA array to device, CUDA array to CUDA array), cuMemcpy2D() may fail for pitches not computed by cuMemAllocPitch(). cuMemcpy2DUnaligned() does not have this restriction, but may run significantly slower in the cases where cuMemcpy2D() would have returned an error code.

Parameters:

pCopy - parameters for the memory copy

ncuMemcpy3D

public static int ncuMemcpy3D(long pCopy)

Unsafe version of: Memcpy3D

cuMemcpy3D

public static int cuMemcpy3D(CUDA_MEMCPY3D pCopy)

Copies memory for 3D arrays.

Perform a 3D memory copy according to the parameters specified in pCopy.

If srcMemoryType is MEMORYTYPE_UNIFIED, srcDevice and srcPitch specify the (unified virtual address space) base address of the source data and the bytes per row to apply. srcArray is ignored. This value may be used only if unified addressing is supported in the calling context.

If srcMemoryType is MEMORYTYPE_HOST, srcHost, srcPitch and srcHeight specify the (host) base address of the source data, the bytes per row, and the height of each 2D slice of the 3D array. srcArray is ignored.

If srcMemoryType is MEMORYTYPE_DEVICE, srcDevice, srcPitch and srcHeight specify the (device) base address of the source data, the bytes per row, and the height of each 2D slice of the 3D array. srcArray is ignored.

If srcMemoryType is MEMORYTYPE_ARRAY, srcArray specifies the handle of the source data. srcHost, srcDevice, srcPitch and srcHeight are ignored.

If dstMemoryType is MEMORYTYPE_UNIFIED, dstDevice and dstPitch specify the (unified virtual address space) base address of the source data and the bytes per row to apply. dstArray is ignored. This value may be used only if unified addressing is supported in the calling context.

If dstMemoryType is MEMORYTYPE_HOST, dstHost and dstPitch specify the (host) base address of the destination data, the bytes per row, and the height of each 2D slice of the 3D array. dstArray is ignored.

If dstMemoryType is MEMORYTYPE_DEVICE, dstDevice and dstPitch specify the (device) base address of the destination data, the bytes per row, and the height of each 2D slice of the 3D array. dstArray is ignored.

If dstMemoryType is MEMORYTYPE_ARRAY, dstArray specifies the handle of the destination data. dstHost, dstDevice, dstPitch and dstHeight are ignored.

srcXInBytes, srcY and srcZ specify the base address of the source data for the copy.

For host pointers, the starting address is

   void* Start = (void*)((char*)srcHost+(srcZ*srcHeight+srcY)*srcPitch + srcXInBytes);

For device pointers, the starting address is

   CUdeviceptr Start = srcDevice+(srcZ*srcHeight+srcY)*srcPitch+srcXInBytes;

For CUDA arrays, srcXInBytes must be evenly divisible by the array element size.

dstXInBytes, dstY and dstZ specify the base address of the destination data for the copy.

For host pointers, the base address is

   void* dstStart = (void*)((char*)dstHost+(dstZ*dstHeight+dstY)*dstPitch + dstXInBytes);

For device pointers, the starting address is

   CUdeviceptr dstStart = dstDevice+(dstZ*dstHeight+dstY)*dstPitch+dstXInBytes;

For CUDA arrays, dstXInBytes must be evenly divisible by the array element size.

WidthInBytes, Height and Depth specify the width (in bytes), height and depth of the 3D copy being performed.

If specified, srcPitch must be greater than or equal to WidthInBytes + srcXInBytes, and dstPitch must be greater than or equal to WidthInBytes + dstXInBytes.

If specified, srcHeight must be greater than or equal to Height + srcY, and dstHeight must be greater than or equal to Height + dstY.

Memcpy3D returns an error if any pitch is greater than the maximum allowed (DEVICE_ATTRIBUTE_MAX_PITCH).

The srcLOD and dstLOD members of the CUDA_MEMCPY3D structure must be set to 0.

Note

_sync

Parameters:

pCopy - parameters for the memory copy

ncuMemcpy3DPeer

public static int ncuMemcpy3DPeer(long pCopy)

Unsafe version of: Memcpy3DPeer

cuMemcpy3DPeer

public static int cuMemcpy3DPeer(CUDA_MEMCPY3D_PEER pCopy)

Copies memory between contexts.

Perform a 3D memory copy according to the parameters specified in pCopy.

Parameters:

pCopy - parameters for the memory copy

cuMemcpyAsync

public static int cuMemcpyAsync(long dst,
 long src,
 long ByteCount,
 long hStream)

Copies memory asynchronously.

Copies data between two pointers. dst and src are base pointers of the destination and source, respectively. ByteCount specifies the number of bytes to copy. Note that this function infers the type of the transfer (host to host, host to device, device to device, or device to host) from the pointer values. This function is only allowed in contexts which support unified addressing.

Parameters:

dst - destination unified virtual address space pointer

src - source unified virtual address space pointer

ByteCount - size of memory copy in bytes

hStream - stream identifier

cuMemcpyPeerAsync

public static int cuMemcpyPeerAsync(long dstDevice,
 long dstContext,
 long srcDevice,
 long srcContext,
 long ByteCount,
 long hStream)

Copies device memory between two contexts asynchronously.

Copies from device memory in one context to device memory in another context. dstDevice is the base device pointer of the destination memory and dstContext is the destination context. srcDevice is the base device pointer of the source memory and srcContext is the source pointer. ByteCount specifies the number of bytes to copy.

Parameters:

dstDevice - destination device pointer

dstContext - destination context

srcDevice - source device pointer

srcContext - source context

ByteCount - size of memory copy in bytes

hStream - stream identifier

ncuMemcpyHtoDAsync

public static int ncuMemcpyHtoDAsync(long dstDevice,
 long srcHost,
 long ByteCount,
 long hStream)

Unsafe version of: MemcpyHtoDAsync

Parameters:

ByteCount - size of memory copy in bytes

cuMemcpyHtoDAsync

public static int cuMemcpyHtoDAsync(long dstDevice,
 ByteBuffer srcHost,
 long hStream)

Copies memory from Host to Device.

Copies from host memory to device memory. dstDevice and srcHost are the base addresses of the destination and source, respectively. ByteCount specifies the number of bytes to copy.

Parameters:

dstDevice - destination device pointer

srcHost - source host pointer

hStream - stream identifier

cuMemcpyHtoDAsync

public static int cuMemcpyHtoDAsync(long dstDevice,
 ShortBuffer srcHost,
 long hStream)

Copies memory from Host to Device.

Copies from host memory to device memory. dstDevice and srcHost are the base addresses of the destination and source, respectively. ByteCount specifies the number of bytes to copy.

Parameters:

dstDevice - destination device pointer

srcHost - source host pointer

hStream - stream identifier

cuMemcpyHtoDAsync

public static int cuMemcpyHtoDAsync(long dstDevice,
 IntBuffer srcHost,
 long hStream)

Copies memory from Host to Device.

Copies from host memory to device memory. dstDevice and srcHost are the base addresses of the destination and source, respectively. ByteCount specifies the number of bytes to copy.

Parameters:

dstDevice - destination device pointer

srcHost - source host pointer

hStream - stream identifier

cuMemcpyHtoDAsync

public static int cuMemcpyHtoDAsync(long dstDevice,
 LongBuffer srcHost,
 long hStream)

Copies memory from Host to Device.

Copies from host memory to device memory. dstDevice and srcHost are the base addresses of the destination and source, respectively. ByteCount specifies the number of bytes to copy.

Parameters:

dstDevice - destination device pointer

srcHost - source host pointer

hStream - stream identifier

cuMemcpyHtoDAsync

public static int cuMemcpyHtoDAsync(long dstDevice,
 FloatBuffer srcHost,
 long hStream)

Copies memory from Host to Device.

Copies from host memory to device memory. dstDevice and srcHost are the base addresses of the destination and source, respectively. ByteCount specifies the number of bytes to copy.

Parameters:

dstDevice - destination device pointer

srcHost - source host pointer

hStream - stream identifier

cuMemcpyHtoDAsync

public static int cuMemcpyHtoDAsync(long dstDevice,
 DoubleBuffer srcHost,
 long hStream)

Copies memory from Host to Device.

Copies from host memory to device memory. dstDevice and srcHost are the base addresses of the destination and source, respectively. ByteCount specifies the number of bytes to copy.

Parameters:

dstDevice - destination device pointer

srcHost - source host pointer

hStream - stream identifier

cuMemcpyHtoDAsync

public static int cuMemcpyHtoDAsync(long dstDevice,
 PointerBuffer srcHost,
 long hStream)

Copies memory from Host to Device.

Copies from host memory to device memory. dstDevice and srcHost are the base addresses of the destination and source, respectively. ByteCount specifies the number of bytes to copy.

Parameters:

dstDevice - destination device pointer

srcHost - source host pointer

hStream - stream identifier

ncuMemcpyDtoHAsync

public static int ncuMemcpyDtoHAsync(long dstHost,
 long srcDevice,
 long ByteCount,
 long hStream)

Unsafe version of: MemcpyDtoHAsync

Parameters:

ByteCount - size of memory copy in bytes

cuMemcpyDtoHAsync

public static int cuMemcpyDtoHAsync(ByteBuffer dstHost,
 long srcDevice,
 long hStream)

Copies memory from Device to Host.

Copies from device to host memory. dstHost and srcDevice specify the base pointers of the destination and source, respectively. ByteCount specifies the number of bytes to copy.

Parameters:

dstHost - destination host pointer

srcDevice - source device pointer

hStream - stream identifier

cuMemcpyDtoHAsync

public static int cuMemcpyDtoHAsync(ShortBuffer dstHost,
 long srcDevice,
 long hStream)

Copies memory from Device to Host.

Copies from device to host memory. dstHost and srcDevice specify the base pointers of the destination and source, respectively. ByteCount specifies the number of bytes to copy.

Parameters:

dstHost - destination host pointer

srcDevice - source device pointer

hStream - stream identifier

cuMemcpyDtoHAsync

public static int cuMemcpyDtoHAsync(IntBuffer dstHost,
 long srcDevice,
 long hStream)

Copies memory from Device to Host.

Copies from device to host memory. dstHost and srcDevice specify the base pointers of the destination and source, respectively. ByteCount specifies the number of bytes to copy.

Parameters:

dstHost - destination host pointer

srcDevice - source device pointer

hStream - stream identifier

cuMemcpyDtoHAsync

public static int cuMemcpyDtoHAsync(LongBuffer dstHost,
 long srcDevice,
 long hStream)

Copies memory from Device to Host.

Copies from device to host memory. dstHost and srcDevice specify the base pointers of the destination and source, respectively. ByteCount specifies the number of bytes to copy.

Parameters:

dstHost - destination host pointer

srcDevice - source device pointer

hStream - stream identifier

cuMemcpyDtoHAsync

public static int cuMemcpyDtoHAsync(FloatBuffer dstHost,
 long srcDevice,
 long hStream)

Copies memory from Device to Host.

Copies from device to host memory. dstHost and srcDevice specify the base pointers of the destination and source, respectively. ByteCount specifies the number of bytes to copy.

Parameters:

dstHost - destination host pointer

srcDevice - source device pointer

hStream - stream identifier

cuMemcpyDtoHAsync

public static int cuMemcpyDtoHAsync(DoubleBuffer dstHost,
 long srcDevice,
 long hStream)

Copies memory from Device to Host.

Copies from device to host memory. dstHost and srcDevice specify the base pointers of the destination and source, respectively. ByteCount specifies the number of bytes to copy.

Parameters:

dstHost - destination host pointer

srcDevice - source device pointer

hStream - stream identifier

cuMemcpyDtoHAsync

public static int cuMemcpyDtoHAsync(PointerBuffer dstHost,
 long srcDevice,
 long hStream)

Copies memory from Device to Host.

Copies from device to host memory. dstHost and srcDevice specify the base pointers of the destination and source, respectively. ByteCount specifies the number of bytes to copy.

Parameters:

dstHost - destination host pointer

srcDevice - source device pointer

hStream - stream identifier

cuMemcpyDtoDAsync

public static int cuMemcpyDtoDAsync(long dstDevice,
 long srcDevice,
 long ByteCount,
 long hStream)

Copies memory from Device to Device.

Copies from device memory to device memory. dstDevice and srcDevice are the base pointers of the destination and source, respectively. ByteCount specifies the number of bytes to copy.

Parameters:

dstDevice - destination device pointer

srcDevice - source device pointer

ByteCount - size of memory copy in bytes

hStream - stream identifier

ncuMemcpyHtoAAsync

public static int ncuMemcpyHtoAAsync(long dstArray,
 long dstOffset,
 long srcHost,
 long ByteCount,
 long hStream)

Unsafe version of: MemcpyHtoAAsync

Parameters:

ByteCount - size of memory copy in bytes

cuMemcpyHtoAAsync

public static int cuMemcpyHtoAAsync(long dstArray,
 long dstOffset,
 ByteBuffer srcHost,
 long hStream)

Copies memory from Host to Array.

Copies from host memory to a 1D CUDA array. dstArray and dstOffset specify the CUDA array handle and starting offset in bytes of the destination data. srcHost specifies the base address of the source. ByteCount specifies the number of bytes to copy.

Parameters:

dstArray - destination array

dstOffset - offset in bytes of destination array

srcHost - source host pointer

hStream - stream identifier

cuMemcpyHtoAAsync

public static int cuMemcpyHtoAAsync(long dstArray,
 long dstOffset,
 ShortBuffer srcHost,
 long hStream)

Copies memory from Host to Array.

Copies from host memory to a 1D CUDA array. dstArray and dstOffset specify the CUDA array handle and starting offset in bytes of the destination data. srcHost specifies the base address of the source. ByteCount specifies the number of bytes to copy.

Parameters:

dstArray - destination array

dstOffset - offset in bytes of destination array

srcHost - source host pointer

hStream - stream identifier

cuMemcpyHtoAAsync

public static int cuMemcpyHtoAAsync(long dstArray,
 long dstOffset,
 IntBuffer srcHost,
 long hStream)

Copies memory from Host to Array.

Copies from host memory to a 1D CUDA array. dstArray and dstOffset specify the CUDA array handle and starting offset in bytes of the destination data. srcHost specifies the base address of the source. ByteCount specifies the number of bytes to copy.

Parameters:

dstArray - destination array

dstOffset - offset in bytes of destination array

srcHost - source host pointer

hStream - stream identifier

cuMemcpyHtoAAsync

public static int cuMemcpyHtoAAsync(long dstArray,
 long dstOffset,
 LongBuffer srcHost,
 long hStream)

Copies memory from Host to Array.

Copies from host memory to a 1D CUDA array. dstArray and dstOffset specify the CUDA array handle and starting offset in bytes of the destination data. srcHost specifies the base address of the source. ByteCount specifies the number of bytes to copy.

Parameters:

dstArray - destination array

dstOffset - offset in bytes of destination array

srcHost - source host pointer

hStream - stream identifier

cuMemcpyHtoAAsync

public static int cuMemcpyHtoAAsync(long dstArray,
 long dstOffset,
 FloatBuffer srcHost,
 long hStream)

Copies memory from Host to Array.

Copies from host memory to a 1D CUDA array. dstArray and dstOffset specify the CUDA array handle and starting offset in bytes of the destination data. srcHost specifies the base address of the source. ByteCount specifies the number of bytes to copy.

Parameters:

dstArray - destination array

dstOffset - offset in bytes of destination array

srcHost - source host pointer

hStream - stream identifier

cuMemcpyHtoAAsync

public static int cuMemcpyHtoAAsync(long dstArray,
 long dstOffset,
 DoubleBuffer srcHost,
 long hStream)

Copies memory from Host to Array.

Copies from host memory to a 1D CUDA array. dstArray and dstOffset specify the CUDA array handle and starting offset in bytes of the destination data. srcHost specifies the base address of the source. ByteCount specifies the number of bytes to copy.

Parameters:

dstArray - destination array

dstOffset - offset in bytes of destination array

srcHost - source host pointer

hStream - stream identifier

cuMemcpyHtoAAsync

public static int cuMemcpyHtoAAsync(long dstArray,
 long dstOffset,
 PointerBuffer srcHost,
 long hStream)

Copies memory from Host to Array.

Copies from host memory to a 1D CUDA array. dstArray and dstOffset specify the CUDA array handle and starting offset in bytes of the destination data. srcHost specifies the base address of the source. ByteCount specifies the number of bytes to copy.

Parameters:

dstArray - destination array

dstOffset - offset in bytes of destination array

srcHost - source host pointer

hStream - stream identifier

ncuMemcpyAtoHAsync

public static int ncuMemcpyAtoHAsync(long dstHost,
 long srcArray,
 long srcOffset,
 long ByteCount,
 long hStream)

Unsafe version of: MemcpyAtoHAsync

Parameters:

ByteCount - size of memory copy in bytes

cuMemcpyAtoHAsync

public static int cuMemcpyAtoHAsync(ByteBuffer dstHost,
 long srcArray,
 long srcOffset,
 long hStream)

Copies memory from Array to Host.

Copies from one 1D CUDA array to host memory. dstHost specifies the base pointer of the destination. srcArray and srcOffset specify the CUDA array handle and starting offset in bytes of the source data. ByteCount specifies the number of bytes to copy.

Parameters:

dstHost - destination pointer

srcArray - source array

srcOffset - offset in bytes of source array

hStream - stream identifier

cuMemcpyAtoHAsync

public static int cuMemcpyAtoHAsync(ShortBuffer dstHost,
 long srcArray,
 long srcOffset,
 long hStream)

Copies memory from Array to Host.

Copies from one 1D CUDA array to host memory. dstHost specifies the base pointer of the destination. srcArray and srcOffset specify the CUDA array handle and starting offset in bytes of the source data. ByteCount specifies the number of bytes to copy.

Parameters:

dstHost - destination pointer

srcArray - source array

srcOffset - offset in bytes of source array

hStream - stream identifier

cuMemcpyAtoHAsync

public static int cuMemcpyAtoHAsync(IntBuffer dstHost,
 long srcArray,
 long srcOffset,
 long hStream)

Copies memory from Array to Host.

Copies from one 1D CUDA array to host memory. dstHost specifies the base pointer of the destination. srcArray and srcOffset specify the CUDA array handle and starting offset in bytes of the source data. ByteCount specifies the number of bytes to copy.

Parameters:

dstHost - destination pointer

srcArray - source array

srcOffset - offset in bytes of source array

hStream - stream identifier

cuMemcpyAtoHAsync

public static int cuMemcpyAtoHAsync(LongBuffer dstHost,
 long srcArray,
 long srcOffset,
 long hStream)

Copies memory from Array to Host.

Copies from one 1D CUDA array to host memory. dstHost specifies the base pointer of the destination. srcArray and srcOffset specify the CUDA array handle and starting offset in bytes of the source data. ByteCount specifies the number of bytes to copy.

Parameters:

dstHost - destination pointer

srcArray - source array

srcOffset - offset in bytes of source array

hStream - stream identifier

cuMemcpyAtoHAsync

public static int cuMemcpyAtoHAsync(FloatBuffer dstHost,
 long srcArray,
 long srcOffset,
 long hStream)

Copies memory from Array to Host.

Copies from one 1D CUDA array to host memory. dstHost specifies the base pointer of the destination. srcArray and srcOffset specify the CUDA array handle and starting offset in bytes of the source data. ByteCount specifies the number of bytes to copy.

Parameters:

dstHost - destination pointer

srcArray - source array

srcOffset - offset in bytes of source array

hStream - stream identifier

cuMemcpyAtoHAsync

public static int cuMemcpyAtoHAsync(DoubleBuffer dstHost,
 long srcArray,
 long srcOffset,
 long hStream)

Copies memory from Array to Host.

Copies from one 1D CUDA array to host memory. dstHost specifies the base pointer of the destination. srcArray and srcOffset specify the CUDA array handle and starting offset in bytes of the source data. ByteCount specifies the number of bytes to copy.

Parameters:

dstHost - destination pointer

srcArray - source array

srcOffset - offset in bytes of source array

hStream - stream identifier

cuMemcpyAtoHAsync

public static int cuMemcpyAtoHAsync(PointerBuffer dstHost,
 long srcArray,
 long srcOffset,
 long hStream)

Copies memory from Array to Host.

Copies from one 1D CUDA array to host memory. dstHost specifies the base pointer of the destination. srcArray and srcOffset specify the CUDA array handle and starting offset in bytes of the source data. ByteCount specifies the number of bytes to copy.

Parameters:

dstHost - destination pointer

srcArray - source array

srcOffset - offset in bytes of source array

hStream - stream identifier

ncuMemcpy2DAsync

public static int ncuMemcpy2DAsync(long pCopy,
 long hStream)

Unsafe version of: Memcpy2DAsync

cuMemcpy2DAsync

public static int cuMemcpy2DAsync(CUDA_MEMCPY2D pCopy,
 long hStream)

Copies memory for 2D arrays.

Perform a 2D memory copy according to the parameters specified in pCopy.

If srcMemoryType is MEMORYTYPE_HOST, srcHost and srcPitch specify the (host) base address of the source data and the bytes per row to apply. srcArray is ignored.

If srcMemoryType is MEMORYTYPE_UNIFIED, srcDevice and srcPitch specify the (unified virtual address space) base address of the source data and the bytes per row to apply. srcArray is ignored. This value may be used only if unified addressing is supported in the calling context.

If srcMemoryType is MEMORYTYPE_DEVICE, srcDevice and srcPitch specify the (device) base address of the source data and the bytes per row to apply. srcArray is ignored.

If srcMemoryType is MEMORYTYPE_ARRAY, srcArray specifies the handle of the source data. srcHost, srcDevice and srcPitch are ignored.

If dstMemoryType is MEMORYTYPE_UNIFIED, dstDevice and dstPitch specify the (unified virtual address space) base address of the source data and the bytes per row to apply. dstArray is ignored. This value may be used only if unified addressing is supported in the calling context.

If dstMemoryType is MEMORYTYPE_HOST, dstHost and dstPitch specify the (host) base address of the destination data and the bytes per row to apply. dstArray is ignored.

If dstMemoryType is MEMORYTYPE_DEVICE, dstDevice and dstPitch specify the (device) base address of the destination data and the bytes per row to apply. dstArray is ignored.

If dstMemoryType is MEMORYTYPE_ARRAY, dstArray specifies the handle of the destination data. dstHost, dstDevice and dstPitch are ignored.

srcXInBytes and srcY specify the base address of the source data for the copy.

For host pointers, the starting address is

   void* Start = (void*)((char*)srcHost+srcY*srcPitch + srcXInBytes);

For device pointers, the starting address is

   CUdeviceptr Start = srcDevice+srcY*srcPitch+srcXInBytes;

For CUDA arrays, srcXInBytes must be evenly divisible by the array element size.

dstXInBytes and dstY specify the base address of the destination data for the copy.

For host pointers, the base address is

   void* dstStart = (void*)((char*)dstHost+dstY*dstPitch + dstXInBytes);

For device pointers, the starting address is

   CUdeviceptr dstStart = dstDevice+dstY*dstPitch+dstXInBytes;

For CUDA arrays, dstXInBytes must be evenly divisible by the array element size.

WidthInBytes and Height specify the width (in bytes) and height of the 2D copy being performed.

If specified, srcPitch must be greater than or equal to WidthInBytes + srcXInBytes, and dstPitch must be greater than or equal to WidthInBytes + dstXInBytes.

If specified, srcPitch must be greater than or equal to WidthInBytes + srcXInBytes, and dstPitch must be greater than or equal to WidthInBytes + dstXInBytes.

If specified, srcHeight must be greater than or equal to Height + srcY, and dstHeight must be greater than or equal to Height + dstY.

cuMemcpy2DAsync() returns an error if any pitch is greater than the maximum allowed (DEVICE_ATTRIBUTE_MAX_PITCH). MemAllocPitch passes back pitches that always work with Memcpy2D. On intra-device memory copies (device to device, CUDA array to device, CUDA array to CUDA array), cuMemcpy2DAsync() may fail for pitches not computed by cuMemAllocPitch().

Parameters:

pCopy - parameters for the memory copy

hStream - stream identifier

ncuMemcpy3DAsync

public static int ncuMemcpy3DAsync(long pCopy,
 long hStream)

Unsafe version of: Memcpy3DAsync

cuMemcpy3DAsync

public static int cuMemcpy3DAsync(CUDA_MEMCPY3D pCopy,
 long hStream)

Copies memory for 3D arrays.

Perform a 3D memory copy according to the parameters specified in pCopy.

If srcMemoryType is MEMORYTYPE_UNIFIED, srcDevice and srcPitch specify the (unified virtual address space) base address of the source data and the bytes per row to apply. srcArray is ignored. This value may be used only if unified addressing is supported in the calling context.

If srcMemoryType is MEMORYTYPE_HOST, srcHost, srcPitch and srcHeight specify the (host) base address of the source data, the bytes per row, and the height of each 2D slice of the 3D array. srcArray is ignored.

If srcMemoryType is MEMORYTYPE_DEVICE, srcDevice, srcPitch and srcHeight specify the (device) base address of the source data, the bytes per row, and the height of each 2D slice of the 3D array. srcArray is ignored.

If srcMemoryType is MEMORYTYPE_ARRAY, srcArray specifies the handle of the source data. srcHost, srcDevice, srcPitch and srcHeight are ignored.

If dstMemoryType is MEMORYTYPE_UNIFIED, dstDevice and dstPitch specify the (unified virtual address space) base address of the source data and the bytes per row to apply. dstArray is ignored. This value may be used only if unified addressing is supported in the calling context.

If dstMemoryType is MEMORYTYPE_HOST, dstHost and dstPitch specify the (host) base address of the destination data, the bytes per row, and the height of each 2D slice of the 3D array. dstArray is ignored.

If dstMemoryType is MEMORYTYPE_DEVICE, dstDevice and dstPitch specify the (device) base address of the destination data, the bytes per row, and the height of each 2D slice of the 3D array. dstArray is ignored.

If dstMemoryType is MEMORYTYPE_ARRAY, dstArray specifies the handle of the destination data. dstHost, dstDevice, dstPitch and dstHeight are ignored.

- srcXInBytes, srcY and srcZ specify the base address of the source data for the copy.

For host pointers, the starting address is

   void* Start = (void*)((char*)srcHost+(srcZ*srcHeight+srcY)*srcPitch + srcXInBytes);

For device pointers, the starting address is

   CUdeviceptr Start = srcDevice+(srcZ*srcHeight+srcY)*srcPitch+srcXInBytes;

For CUDA arrays, srcXInBytes must be evenly divisible by the array element size.

dstXInBytes, dstY and dstZ specify the base address of the destination data for the copy.

For host pointers, the base address is

   void* dstStart = (void*)((char*)dstHost+(dstZ*dstHeight+dstY)*dstPitch + dstXInBytes);

For device pointers, the starting address is

   CUdeviceptr dstStart = dstDevice+(dstZ*dstHeight+dstY)*dstPitch+dstXInBytes;

For CUDA arrays, dstXInBytes must be evenly divisible by the array element size.

WidthInBytes, Height and Depth specify the width (in bytes), height and depth of the 3D copy being performed.

If specified, srcPitch must be greater than or equal to WidthInBytes + srcXInBytes, and dstPitch must be greater than or equal to WidthInBytes + dstXInBytes.

If specified, srcHeight must be greater than or equal to Height + srcY, and dstHeight must be greater than or equal to Height + dstY.

Memcpy3DAsync returns an error if any pitch is greater than the maximum allowed (DEVICE_ATTRIBUTE_MAX_PITCH).

The srcLOD and dstLOD members of the CUDA_MEMCPY3D structure must be set to 0.

Parameters:

pCopy - parameters for the memory copy

hStream - stream identifier

ncuMemcpy3DPeerAsync

public static int ncuMemcpy3DPeerAsync(long pCopy,
 long hStream)

Unsafe version of: Memcpy3DPeerAsync

cuMemcpy3DPeerAsync

public static int cuMemcpy3DPeerAsync(CUDA_MEMCPY3D_PEER pCopy,
 long hStream)

Copies memory between contexts asynchronously.

Perform a 3D memory copy according to the parameters specified in pCopy.

Parameters:

pCopy - parameters for the memory copy

hStream - stream identifier

cuMemsetD8

public static int cuMemsetD8(long dstDevice,
 byte uc,
 long N)

Initializes device memory.

Sets the memory range of N 8-bit values to the specified value uc.

Parameters:

dstDevice - destination device pointer

uc - value to set

N - number of elements

cuMemsetD16

public static int cuMemsetD16(long dstDevice,
 short us,
 long N)

Initializes device memory.

Sets the memory range of N 16-bit values to the specified value us. The dstDevice pointer must be two byte aligned.

Parameters:

dstDevice - destination device pointer

us - value to set

N - number of elements

cuMemsetD32

public static int cuMemsetD32(long dstDevice,
 int ui,
 long N)

Initializes device memory

Sets the memory range of N 32-bit values to the specified value ui. The dstDevice pointer must be four byte aligned.

Parameters:

dstDevice - destination device pointer

ui - value to set

N - number of elements

cuMemsetD2D8

public static int cuMemsetD2D8(long dstDevice,
 long dstPitch,
 byte uc,
 long Width,
 long Height)

Initializes device memory.

Sets the 2D memory range of Width 8-bit values to the specified value uc. Height specifies the number of rows to set, and dstPitch specifies the number of bytes between each row. This function performs fastest when the pitch is one that has been passed back by MemAllocPitch.

Parameters:

dstDevice - destination device pointer

dstPitch - pitch of destination device pointer(Unused if Height is 1)

uc - value to set

Width - width of row

Height - number of rows

cuMemsetD2D16

public static int cuMemsetD2D16(long dstDevice,
 long dstPitch,
 short us,
 long Width,
 long Height)

Initializes device memory.

Sets the 2D memory range of Width 16-bit values to the specified value us. Height specifies the number of rows to set, and dstPitch specifies the number of bytes between each row. The dstDevice pointer and dstPitch offset must be two byte aligned. This function performs fastest when the pitch is one that has been passed back by MemAllocPitch.

Parameters:

dstDevice - destination device pointer

dstPitch - pitch of destination device pointer(Unused if Height is 1)

us - value to set

Width - width of row

Height - number of rows

cuMemsetD2D32

public static int cuMemsetD2D32(long dstDevice,
 long dstPitch,
 int ui,
 long Width,
 long Height)

Initializes device memory.

Sets the 2D memory range of Width 32-bit values to the specified value ui. Height specifies the number of rows to set, and dstPitch specifies the number of bytes between each row. The dstDevice pointer and dstPitch offset must be four byte aligned. This function performs fastest when the pitch is one that has been passed back by MemAllocPitch.

Parameters:

dstDevice - destination device pointer

dstPitch - pitch of destination device pointer(Unused if Height is 1)

ui - value to set

Width - width of row

Height - number of rows

cuMemsetD8Async

public static int cuMemsetD8Async(long dstDevice,
 byte uc,
 long N,
 long hStream)

Sets device memory

Sets the memory range of N 8-bit values to the specified value uc.

Parameters:

dstDevice - destination device pointer

uc - value to set

N - number of elements

hStream - stream identifier

cuMemsetD16Async

public static int cuMemsetD16Async(long dstDevice,
 short us,
 long N,
 long hStream)

Sets device memory

Sets the memory range of N 16-bit values to the specified value us. The dstDevice pointer must be two byte aligned.

Parameters:

dstDevice - destination device pointer

us - value to set

N - number of elements

hStream - stream identifier

cuMemsetD32Async

public static int cuMemsetD32Async(long dstDevice,
 int ui,
 long N,
 long hStream)

Sets device memory.

Sets the memory range of N 32-bit values to the specified value ui. The dstDevice pointer must be four byte aligned.

Parameters:

dstDevice - destination device pointer

ui - value to set

N - number of elements

hStream - stream identifier

cuMemsetD2D8Async

public static int cuMemsetD2D8Async(long dstDevice,
 long dstPitch,
 byte uc,
 long Width,
 long Height,
 long hStream)

Sets device memory.

Sets the 2D memory range of Width 8-bit values to the specified value uc. Height specifies the number of rows to set, and dstPitch specifies the number of bytes between each row. This function performs fastest when the pitch is one that has been passed back by MemAllocPitch.

Parameters:

dstDevice - destination device pointer

dstPitch - pitch of destination device pointer(Unused if Height is 1)

uc - value to set

Width - width of row

Height - number of rows

hStream - stream identifier

cuMemsetD2D16Async

public static int cuMemsetD2D16Async(long dstDevice,
 long dstPitch,
 short us,
 long Width,
 long Height,
 long hStream)

Sets device memory.

Sets the 2D memory range of Width 16-bit values to the specified value us. Height specifies the number of rows to set, and dstPitch specifies the number of bytes between each row. The dstDevice pointer and dstPitch offset must be two byte aligned. This function performs fastest when the pitch is one that has been passed back by MemAllocPitch.

Parameters:

dstDevice - destination device pointer

dstPitch - pitch of destination device pointer(Unused if Height is 1)

us - value to set

Width - width of row

Height - number of rows

hStream - stream identifier

cuMemsetD2D32Async

public static int cuMemsetD2D32Async(long dstDevice,
 long dstPitch,
 int ui,
 long Width,
 long Height,
 long hStream)

Sets device memory.

Sets the 2D memory range of Width 32-bit values to the specified value ui. Height specifies the number of rows to set, and dstPitch specifies the number of bytes between each row. The dstDevice pointer and dstPitch offset must be four byte aligned. This function performs fastest when the pitch is one that has been passed back by MemAllocPitch.

Parameters:

dstDevice - destination device pointer

dstPitch - pitch of destination device pointer(Unused if Height is 1)

ui - value to set

Width - width of row

Height - number of rows

hStream - stream identifier

ncuArrayCreate

public static int ncuArrayCreate(long pHandle,
 long pAllocateArray)

Unsafe version of: ArrayCreate

cuArrayCreate

public static int cuArrayCreate(PointerBuffer pHandle,
 CUDA_ARRAY_DESCRIPTOR pAllocateArray)

Creates a 1D or 2D CUDA array.

Creates a CUDA array according to the CUDA_ARRAY_DESCRIPTOR structure pAllocateArray and returns a handle to the new CUDA array in *pHandle.

Parameters:

pHandle - returned array

pAllocateArray - array descriptor

ncuArrayGetDescriptor

public static int ncuArrayGetDescriptor(long pArrayDescriptor,
 long hArray)

Unsafe version of: ArrayGetDescriptor

cuArrayGetDescriptor

public static int cuArrayGetDescriptor(CUDA_ARRAY_DESCRIPTOR pArrayDescriptor,
 long hArray)

Get a 1D or 2D CUDA array descriptor.

Returns in *pArrayDescriptor a descriptor containing information on the format and dimensions of the CUDA array hArray. It is useful for subroutines that have been passed a CUDA array, but need to know the CUDA array parameters for validation or other purposes.

Parameters:

pArrayDescriptor - returned array descriptor

hArray - array to get descriptor of

ncuArrayGetSparseProperties

public static int ncuArrayGetSparseProperties(long sparseProperties,
 long array)

Unsafe version of: ArrayGetSparseProperties

cuArrayGetSparseProperties

public static int cuArrayGetSparseProperties(CUDA_ARRAY_SPARSE_PROPERTIES sparseProperties,
 long array)

Returns the layout properties of a sparse CUDA array.

Returns the layout properties of a sparse CUDA array in sparseProperties If the CUDA array is not allocated with flag CUDA_ARRAY3D_SPARSE CUDA_ERROR_INVALID_VALUE will be returned.

If the returned value in CUDA_ARRAY_SPARSE_PROPERTIESflags contains ARRAY_SPARSE_PROPERTIES_SINGLE_MIPTAIL, then CUDA_ARRAY_SPARSE_PROPERTIES::miptailSize represents the total size of the array. Otherwise, it will be zero. Also, the returned value in CUDA_ARRAY_SPARSE_PROPERTIES::miptailFirstLevel is always zero. Note that the array must have been allocated using ArrayCreate or Array3DCreate. For CUDA arrays obtained using MipmappedArrayGetLevel, CUDA_ERROR_INVALID_VALUE will be returned. Instead, MipmappedArrayGetSparseProperties must be used to obtain the sparse properties of the entire CUDA mipmapped array to which array belongs to.

Parameters:

sparseProperties - pointer to CUDA_ARRAY_SPARSE_PROPERTIES

array - CUDA array to get the sparse properties of

ncuMipmappedArrayGetSparseProperties

public static int ncuMipmappedArrayGetSparseProperties(long sparseProperties,
 long mipmap)

Unsafe version of: MipmappedArrayGetSparseProperties

cuMipmappedArrayGetSparseProperties

public static int cuMipmappedArrayGetSparseProperties(CUDA_ARRAY_SPARSE_PROPERTIES sparseProperties,
 long mipmap)

Returns the layout properties of a sparse CUDA mipmapped array.

Returns the sparse array layout properties in sparseProperties If the CUDA mipmapped array is not allocated with flag CUDA_ARRAY3D_SPARSE CUDA_ERROR_INVALID_VALUE will be returned.

For non-layered CUDA mipmapped arrays, CUDA_ARRAY_SPARSE_PROPERTIES::miptailSize returns the size of the mip tail region. The mip tail region includes all mip levels whose width, height or depth is less than that of the tile. For layered CUDA mipmapped arrays, if CUDA_ARRAY_SPARSE_PROPERTIES::flags contains ARRAY_SPARSE_PROPERTIES_SINGLE_MIPTAIL, then CUDA_ARRAY_SPARSE_PROPERTIES::miptailSize specifies the size of the mip tail of all layers combined. Otherwise, CUDA_ARRAY_SPARSE_PROPERTIES::miptailSize specifies mip tail size per layer. The returned value of CUDA_ARRAY_SPARSE_PROPERTIES::miptailFirstLevel is valid only if CUDA_ARRAY_SPARSE_PROPERTIES::miptailSize is non-zero.

Parameters:

sparseProperties - pointer to CUDA_ARRAY_SPARSE_PROPERTIES

mipmap - CUDA mipmapped array to get the sparse properties of

ncuArrayGetPlane

public static int ncuArrayGetPlane(long pPlaneArray,
 long hArray,
 int planeIdx)

Unsafe version of: ArrayGetPlane

cuArrayGetPlane

public static int cuArrayGetPlane(PointerBuffer pPlaneArray,
 long hArray,
 int planeIdx)

Gets a CUDA array plane from a CUDA array.

Returns in pPlaneArray a CUDA array that represents a single format plane of the CUDA array hArray.

If planeIdx is greater than the maximum number of planes in this array or if the array does not have a multi-planar format e.g: AD_FORMAT_NV12, then CUDA_ERROR_INVALID_VALUE is returned.

Note that if the hArray has format AD_FORMAT_NV12, then passing in 0 for planeIdx returns a CUDA array of the same size as hArray but with one channel and AD_FORMAT_UNSIGNED_INT8 as its format. If 1 is passed for planeIdx, then the returned CUDA array has half the height and width of hArray with two channels and AD_FORMAT_UNSIGNED_INT8 as its format.

Parameters:

pPlaneArray - returned CUDA array referenced by the planeIdx

hArray - multiplanar CUDA array

planeIdx - plane index

cuArrayDestroy

public static int cuArrayDestroy(long hArray)

Destroys a CUDA array.

Destroys the CUDA array hArray.

Parameters:

hArray - array to destroy

ncuArray3DCreate

public static int ncuArray3DCreate(long pHandle,
 long pAllocateArray)

Unsafe version of: Array3DCreate

cuArray3DCreate

public static int cuArray3DCreate(PointerBuffer pHandle,
 CUDA_ARRAY3D_DESCRIPTOR pAllocateArray)

Creates a 3D CUDA array.

Creates a CUDA array according to the CUDA_ARRAY3D_DESCRIPTOR structure pAllocateArray and returns a handle to the new CUDA array in pHandle.

• Width, Height, and Depth are the width, height, and depth of the CUDA array (in elements); the following types of CUDA arrays can be allocated:
  • A 1D array is allocated if Height and Depth extents are both zero.
  • A 2D array is allocated if only Depth extent is zero.
  • A 3D array is allocated if all three extents are non-zero.
  • A 1D layered CUDA array is allocated if only Height is zero and the CUDA_ARRAY3D_LAYERED flag is set. Each layer is a 1D array. The number of layers is determined by the depth extent.
  • A 2D layered CUDA array is allocated if all three extents are non-zero and the CUDA_ARRAY3D_LAYERED flag is set. Each layer is a 2D array. The number of layers is determined by the depth extent.
  • A cubemap CUDA array is allocated if all three extents are non-zero and the CUDA_ARRAY3D_CUBEMAP flag is set. Width must be equal to Height, and Depth must be six. A cubemap is a special type of 2D layered CUDA array, where the six layers represent the six faces of a cube. The order of the six layers in memory is the same as that listed in CUarray_cubemap_face.
  • A cubemap layered CUDA array is allocated if all three extents are non-zero, and both, CUDA_ARRAY3D_CUBEMAP and CUDA_ARRAY3D_LAYERED flags are set. Width must be equal to Height, and Depth must be a multiple of six. A cubemap layered CUDA array is a special type of 2D layered CUDA array that consists of a collection of cubemaps. The first six layers represent the first cubemap, the next six layers form the second cubemap, and so on.
• Format specifies the format of the elements.
• NumChannels specifies the number of packed components per CUDA array element; it may be 1, 2, or 4;
• Flags may be set to
  • CUDA_ARRAY3D_LAYERED to enable creation of layered CUDA arrays. If this flag is set, Depth specifies the number of layers, not the depth of a 3D array.
  • CUDA_ARRAY3D_SURFACE_LDST to enable surface references to be bound to the CUDA array. If this flag is not set, SurfRefSetArray will fail when attempting to bind the CUDA array to a surface reference.
  • CUDA_ARRAY3D_CUBEMAP to enable creation of cubemaps. If this flag is set, Width must be equal to Height, and Depth must be six. If the CUDA_ARRAY3D_LAYERED flag is also set, then Depth must be a multiple of six.
  • CUDA_ARRAY3D_TEXTURE_GATHER to indicate that the CUDA array will be used for texture gather. Texture gather can only be performed on 2D CUDA arrays.

Width, Height and Depth must meet certain size requirements as listed in the following table. All values are specified in elements. Note that for brevity's sake, the full name of the device attribute is not specified. For ex., TEXTURE1D_WIDTH refers to the device attribute DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH.

Note that 2D CUDA arrays have different size requirements if the CUDA_ARRAY3D_TEXTURE_GATHER flag is set. Width and Height must not be greater than DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH and DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT respectively, in that case.

CUDA array type	Valid extents that must always be met {(width range in elements), (height range), (depth range)}	Valid extents with CUDA_ARRAY3D_SURFACE_LDST set {(width range in elements), (height range), (depth range)}
1D	{ (1,TEXTURE1D_WIDTH), 0, 0 }	{ (1,SURFACE1D_WIDTH), 0, 0 }
2D	{ (1,TEXTURE2D_WIDTH), (1,TEXTURE2D_HEIGHT), 0 }	{ (1,SURFACE2D_WIDTH), (1,SURFACE2D_HEIGHT), 0 }
3D	{ (1,TEXTURE3D_WIDTH), (1,TEXTURE3D_HEIGHT), (1,TEXTURE3D_DEPTH) } OR { (1,TEXTURE3D_WIDTH_ALTERNATE), (1,TEXTURE3D_HEIGHT_ALTERNATE), (1,TEXTURE3D_DEPTH_ALTERNATE) }	{ (1,SURFACE3D_WIDTH), (1,SURFACE3D_HEIGHT), (1,SURFACE3D_DEPTH) }
1D Layered	{ (1,TEXTURE1D_LAYERED_WIDTH), 0, (1,TEXTURE1D_LAYERED_LAYERS) }	{ (1,SURFACE1D_LAYERED_WIDTH), 0, (1,SURFACE1D_LAYERED_LAYERS) }
2D Layered	{ (1,TEXTURE2D_LAYERED_WIDTH), (1,TEXTURE2D_LAYERED_HEIGHT), (1,TEXTURE2D_LAYERED_LAYERS) }	{ (1,SURFACE2D_LAYERED_WIDTH), (1,SURFACE2D_LAYERED_HEIGHT), (1,SURFACE2D_LAYERED_LAYERS) }
Cubemap	{ (1,TEXTURECUBEMAP_WIDTH), (1,TEXTURECUBEMAP_WIDTH), 6 }	{ (1,SURFACECUBEMAP_WIDTH), (1,SURFACECUBEMAP_WIDTH), 6 }
Cubemap Layered	{ (1,TEXTURECUBEMAP_LAYERED_WIDTH), (1,TEXTURECUBEMAP_LAYERED_WIDTH), (1,TEXTURECUBEMAP_LAYERED_LAYERS) }	{ (1,SURFACECUBEMAP_LAYERED_WIDTH), (1,SURFACECUBEMAP_LAYERED_WIDTH), (1,SURFACECUBEMAP_LAYERED_LAYERS) }

Parameters:

pHandle - returned array

pAllocateArray - 3D array descriptor

ncuArray3DGetDescriptor

public static int ncuArray3DGetDescriptor(long pArrayDescriptor,
 long hArray)

Unsafe version of: Array3DGetDescriptor

cuArray3DGetDescriptor

public static int cuArray3DGetDescriptor(CUDA_ARRAY3D_DESCRIPTOR pArrayDescriptor,
 long hArray)

Get a 3D CUDA array descriptor.

Returns in *pArrayDescriptor a descriptor containing information on the format and dimensions of the CUDA array hArray. It is useful for subroutines that have been passed a CUDA array, but need to know the CUDA array parameters for validation or other purposes.

This function may be called on 1D and 2D arrays, in which case the Height and/or Depth members of the descriptor struct will be set to 0.

Parameters:

pArrayDescriptor - returned 3D array descriptor

hArray - 3D array to get descriptor of

ncuMipmappedArrayCreate

public static int ncuMipmappedArrayCreate(long pHandle,
 long pMipmappedArrayDesc,
 int numMipmapLevels)

Unsafe version of: MipmappedArrayCreate

cuMipmappedArrayCreate

public static int cuMipmappedArrayCreate(PointerBuffer pHandle,
 CUDA_ARRAY3D_DESCRIPTOR pMipmappedArrayDesc,
 int numMipmapLevels)

Creates a CUDA mipmapped array.

Creates a CUDA mipmapped array according to the CUDA_ARRAY3D_DESCRIPTOR structure pMipmappedArrayDesc and returns a handle to the new CUDA mipmapped array in *pHandle. numMipmapLevels specifies the number of mipmap levels to be allocated. This value is clamped to the range [1, 1 + floor(log2(max(width, height, depth)))].

• Width, Height, and Depth are the width, height, and depth of the CUDA array (in elements); the following types of CUDA arrays can be allocated:
  • A 1D mipmapped array is allocated if Height and Depth extents are both zero.
  • A 2D mipmapped array is allocated if only Depth extent is zero.
  • A 3D mipmapped array is allocated if all three extents are non-zero.
  • A 1D layered CUDA mipmapped array is allocated if only Height is zero and the CUDA_ARRAY3D_LAYERED flag is set. Each layer is a 1D array. The number of layers is determined by the depth extent.
  • A 2D layered CUDA mipmapped array is allocated if all three extents are non-zero and the CUDA_ARRAY3D_LAYERED flag is set. Each layer is a 2D array. The number of layers is determined by the depth extent.
  • A cubemap CUDA mipmapped array is allocated if all three extents are non-zero and the CUDA_ARRAY3D_CUBEMAP flag is set. Width must be equal to Height, and Depth must be six. A cubemap is a special type of 2D layered CUDA array, where the six layers represent the six faces of a cube. The order of the six layers in memory is the same as that listed in CUarray_cubemap_face.
  • A cubemap layered CUDA mipmapped array is allocated if all three extents are non-zero, and both, CUDA_ARRAY3D_CUBEMAP and CUDA_ARRAY3D_LAYERED flags are set. Width must be equal to Height, and Depth must be a multiple of six. A cubemap layered CUDA array is a special type of 2D layered CUDA array that consists of a collection of cubemaps. The first six layers represent the first cubemap, the next six layers form the second cubemap, and so on.
• Format specifies the format of the elements.
• NumChannels specifies the number of packed components per CUDA array element; it may be 1, 2, or 4;
• Flags may be set to:
  • CUDA_ARRAY3D_LAYERED to enable creation of layered CUDA mipmapped arrays. If this flag is set, Depth specifies the number of layers, not the depth of a 3D array.
  • CUDA_ARRAY3D_SURFACE_LDST to enable surface references to be bound to individual mipmap levels of the CUDA mipmapped array. If this flag is not set, SurfRefSetArray will fail when attempting to bind a mipmap level of the CUDA mipmapped array to a surface reference.
  • CUDA_ARRAY3D_CUBEMAP to enable creation of mipmapped cubemaps. If this flag is set, Width must be equal to Height, and Depth must be six. If the CUDA_ARRAY3D_LAYERED flag is also set, then Depth must be a multiple of six.
  • CUDA_ARRAY3D_TEXTURE_GATHER to indicate that the CUDA mipmapped array will be used for texture gather. Texture gather can only be performed on 2D CUDA mipmapped arrays.

Width, Height and Depth must meet certain size requirements as listed in the following table. All values are specified in elements. Note that for brevity's sake, the full name of the device attribute is not specified. For ex., TEXTURE1D_MIPMAPPED_WIDTH refers to the device attribute DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH.

CUDA array type	Valid extents that must always be met {(width range in elements), (height range), (depth range)}	Valid extents with CUDA_ARRAY3D_SURFACE_LDST set {(width range in elements), (height range), (depth range)}
1D	{ (1,TEXTURE1D_MIPMAPPED_WIDTH), 0, 0 }	{ (1,SURFACE1D_WIDTH), 0, 0 }
2D	{ (1,TEXTURE2D_MIPMAPPED_WIDTH), (1,TEXTURE2D_MIPMAPPED_HEIGHT), 0 }	{ (1,SURFACE2D_WIDTH), (1,SURFACE2D_HEIGHT), 0 }
3D	{ (1,TEXTURE3D_WIDTH), (1,TEXTURE3D_HEIGHT), (1,TEXTURE3D_DEPTH) } OR { (1,TEXTURE3D_WIDTH_ALTERNATE), (1,TEXTURE3D_HEIGHT_ALTERNATE), (1,TEXTURE3D_DEPTH_ALTERNATE) }	{ (1,SURFACE3D_WIDTH), (1,SURFACE3D_HEIGHT), (1,SURFACE3D_DEPTH) }
1D Layered	{ (1,TEXTURE1D_LAYERED_WIDTH), 0, (1,TEXTURE1D_LAYERED_LAYERS) }	{ (1,SURFACE1D_LAYERED_WIDTH), 0, (1,SURFACE1D_LAYERED_LAYERS) }
2D Layered	{ (1,TEXTURE2D_LAYERED_WIDTH), (1,TEXTURE2D_LAYERED_HEIGHT), (1,TEXTURE2D_LAYERED_LAYERS) }	{ (1,SURFACE2D_LAYERED_WIDTH), (1,SURFACE2D_LAYERED_HEIGHT), (1,SURFACE2D_LAYERED_LAYERS) }
Cubemap	{ (1,TEXTURECUBEMAP_WIDTH), (1,TEXTURECUBEMAP_WIDTH), 6 }	{ (1,SURFACECUBEMAP_WIDTH), (1,SURFACECUBEMAP_WIDTH), 6 }
Cubemap Layered	{ (1,TEXTURECUBEMAP_LAYERED_WIDTH), (1,TEXTURECUBEMAP_LAYERED_WIDTH), (1,TEXTURECUBEMAP_LAYERED_LAYERS) }	{ (1,SURFACECUBEMAP_LAYERED_WIDTH), (1,SURFACECUBEMAP_LAYERED_WIDTH), (1,SURFACECUBEMAP_LAYERED_LAYERS) }

Parameters:

pHandle - returned mipmapped array

pMipmappedArrayDesc - mipmapped array descriptor

numMipmapLevels - number of mipmap levels

ncuMipmappedArrayGetLevel

public static int ncuMipmappedArrayGetLevel(long pLevelArray,
 long hMipmappedArray,
 int level)

Unsafe version of: MipmappedArrayGetLevel

cuMipmappedArrayGetLevel

public static int cuMipmappedArrayGetLevel(PointerBuffer pLevelArray,
 long hMipmappedArray,
 int level)

Gets a mipmap level of a CUDA mipmapped array.

Returns in *pLevelArray a CUDA array that represents a single mipmap level of the CUDA mipmapped array hMipmappedArray.

If level is greater than the maximum number of levels in this mipmapped array, CUDA_ERROR_INVALID_VALUE is returned.

Parameters:

pLevelArray - returned mipmap level CUDA array

hMipmappedArray - CUDA mipmapped array

level - mipmap level

cuMipmappedArrayDestroy

public static int cuMipmappedArrayDestroy(long hMipmappedArray)

Destroys a CUDA mipmapped array.

Destroys the CUDA mipmapped array hMipmappedArray.

Parameters:

hMipmappedArray - mipmapped array to destroy

ncuMemAddressReserve

public static int ncuMemAddressReserve(long ptr,
 long size,
 long alignment,
 long addr,
 long flags)

Unsafe version of: MemAddressReserve

cuMemAddressReserve

public static int cuMemAddressReserve(PointerBuffer ptr,
 long size,
 long alignment,
 long addr,
 long flags)

Allocate an address range reservation.

Reserves a virtual address range based on the given parameters, giving the starting address of the range in ptr. This API requires a system that supports UVA. The size and address parameters must be a multiple of the host page size and the alignment must be a power of two or zero for default alignment.

Parameters:

ptr - resulting pointer to start of virtual address range allocated

size - size of the reserved virtual address range requested

alignment - alignment of the reserved virtual address range requested

addr - fixed starting address range requested

flags - currently unused, must be zero

cuMemAddressFree

public static int cuMemAddressFree(long ptr,
 long size)

Free an address range reservation.

Frees a virtual address range reserved by MemAddressReserve. The size must match what was given to memAddressReserve and the ptr given must match what was returned from memAddressReserve.

Parameters:

ptr - starting address of the virtual address range to free

size - size of the virtual address region to free

ncuMemCreate

public static int ncuMemCreate(long handle,
 long size,
 long prop,
 long flags)

Unsafe version of: MemCreate

cuMemCreate

public static int cuMemCreate(LongBuffer handle,
 long size,
 CUmemAllocationProp prop,
 long flags)

Create a CUDA memory handle representing a memory allocation of a given size described by the given properties.

This creates a memory allocation on the target device specified through the prop strcuture. The created allocation will not have any device or host mappings. The generic memory handle for the allocation can be mapped to the address space of calling process via MemMap. This handle cannot be transmitted directly to other processes (see MemExportToShareableHandle). On Windows, the caller must also pass an LPSECURITYATTRIBUTE in prop to be associated with this handle which limits or allows access to this handle for a recepient process (see CUmemAllocationProp::win32HandleMetaData for more). The size of this allocation must be a multiple of the the value given via MemGetAllocationGranularity with the MEM_ALLOC_GRANULARITY_MINIMUM flag. If CUmemAllocationProp::allocFlags::usage contains MEM_CREATE_USAGE_TILE_POOL flag then the memory allocation is intended only to be used as backing tile pool for sparse CUDA arrays and sparse CUDA mipmapped arrays. (see MemMapArrayAsync).

Parameters:

handle - value of handle returned. All operations on this allocation are to be performed using this handle.

size - size of the allocation requested

prop - properties of the allocation to create

flags - flags for future use, must be zero now

cuMemRelease

public static int cuMemRelease(long handle)

Release a memory handle representing a memory allocation which was previously allocated through MemCreate.

Frees the memory that was allocated on a device through cuMemCreate.

The memory allocation will be freed when all outstanding mappings to the memory are unmapped and when all outstanding references to the handle (including it's shareable counterparts) are also released. The generic memory handle can be freed when there are still outstanding mappings made with this handle. Each time a recepient process imports a shareable handle, it needs to pair it with MemRelease for the handle to be freed. If handle is not a valid handle the behavior is undefined.

Parameters:

handle - value of handle which was returned previously by cuMemCreate

cuMemMap

public static int cuMemMap(long ptr,
 long size,
 long offset,
 long handle,
 long flags)

Maps an allocation handle to a reserved virtual address range.

Maps bytes of memory represented by handle starting from byte offset to size to address range [ addr, addr + size]. This range must be an address reservation previously reserved with MemAddressReserve, and offset + size must be less than the size of the memory allocation. Both ptr, size, and offset must be a multiple of the value given via MemGetAllocationGranularity with the MEM_ALLOC_GRANULARITY_MINIMUM flag.

Please note calling MemMap does not make the address accessible, the caller needs to update accessibility of a contiguous mapped VA range by calling MemSetAccess.

Once a recipient process obtains a shareable memory handle from MemImportFromShareableHandle, the process must use MemMap to map the memory into its address ranges before setting accessibility with MemSetAccess.

MemMap can only create mappings on VA range reservations that are not currently mapped.

Parameters:

ptr - address where memory will be mapped

size - size of the memory mapping

offset - offset into the memory represented by - handle from which to start mapping - Note: currently must be zero

handle - handle to a shareable memory

flags - flags for future use, must be zero now

ncuMemMapArrayAsync

public static int ncuMemMapArrayAsync(long mapInfoList,
 int count,
 long hStream)

Unsafe version of: MemMapArrayAsync

Parameters:

count - count of CUarrayMapInfo in mapInfoList

cuMemMapArrayAsync

public static int cuMemMapArrayAsync(CUarrayMapInfo.Buffer mapInfoList,
 long hStream)

Maps or unmaps subregions of sparse CUDA arrays and sparse CUDA mipmapped arrays.

Performs map or unmap operations on subregions of sparse CUDA arrays and sparse CUDA mipmapped arrays. Each operation is specified by a CUarrayMapInfo entry in the mapInfoList array of size count.

where CUarrayMapInfo::resourceType specifies the type of resource to be operated on. If CUarrayMapInfo::resourceType is set to RESOURCE_TYPE_ARRAY then CUarrayMapInfo::resource::array must be set to a valid sparse CUDA array handle. The CUDA array must be either a 2D, 2D layered or 3D CUDA array and must have been allocated using ArrayCreate or Array3DCreate with the flag CUDA_ARRAY3D_SPARSE. For CUDA arrays obtained using MipmappedArrayGetLevel, CUDA_ERROR_INVALID_VALUE will be returned. If CUarrayMapInfo::resourceType is set to RESOURCE_TYPE_MIPMAPPED_ARRAY then CUarrayMapInfo::resource::mipmap must be set to a valid sparse CUDA mipmapped array handle. The CUDA mipmapped array must be either a 2D, 2D layered or 3D CUDA mipmapped array and must have been allocated using MipmappedArrayCreate with the flag CUDA_ARRAY3D_SPARSE.

CUarrayMapInfo::subresourceType specifies the type of subresource within the resource.

where ARRAY_SPARSE_SUBRESOURCE_TYPE_SPARSE_LEVEL indicates a sparse-miplevel which spans at least one tile in every dimension. The remaining miplevels which are too small to span at least one tile in any dimension constitute the mip tail region as indicated by ARRAY_SPARSE_SUBRESOURCE_TYPE_MIPTAIL subresource type.

If CUarrayMapInfo::subresourceType is set to ARRAY_SPARSE_SUBRESOURCE_TYPE_SPARSE_LEVEL then CUarrayMapInfo::subresource::sparseLevel struct must contain valid array subregion offsets and extents. The CUarrayMapInfo::subresource::sparseLevel::offsetX, CUarrayMapInfo::subresource::sparseLevel::offsetY and CUarrayMapInfo::subresource::sparseLevel::offsetZ must specify valid X, Y and Z offsets respectively. The CUarrayMapInfo::subresource::sparseLevel::extentWidth, CUarrayMapInfo::subresource::sparseLevel::extentHeight and CUarrayMapInfo::subresource::sparseLevel::extentDepth must specify valid width, height and depth extents respectively. These offsets and extents must be aligned to the corresponding tile dimension. For CUDA mipmapped arrays CUarrayMapInfo::subresource::sparseLevel::level must specify a valid mip level index. Otherwise, must be zero. For layered CUDA arrays and layered CUDA mipmapped arrays CUarrayMapInfo::subresource::sparseLevel::layer must specify a valid layer index. Otherwise, must be zero. CUarrayMapInfo::subresource::sparseLevel::offsetZ must be zero and CUarrayMapInfo::subresource::sparseLevel::extentDepth must be set to 1 for 2D and 2D layered CUDA arrays and CUDA mipmapped arrays. Tile extents can be obtained by calling ArrayGetSparseProperties and MipmappedArrayGetSparseProperties

If CUarrayMapInfo::subresourceType is set to ARRAY_SPARSE_SUBRESOURCE_TYPE_MIPTAIL then CUarrayMapInfo::subresource::miptail struct must contain valid mip tail offset in CUarrayMapInfo::subresource::miptail::offset and size in CUarrayMapInfo::subresource::miptail::size. Both, mip tail offset and mip tail size must be aligned to the tile size. For layered CUDA mipmapped arrays which don't have the flag ARRAY_SPARSE_PROPERTIES_SINGLE_MIPTAIL set in CUDA_ARRAY_SPARSE_PROPERTIES::flags as returned by MipmappedArrayGetSparseProperties, CUarrayMapInfo::subresource::miptail::layer must specify a valid layer index. Otherwise, must be zero.

CUarrayMapInfo::memOperationType specifies the type of operation.

If CUarrayMapInfo::memOperationType is set to MEM_OPERATION_TYPE_MAP then the subresource will be mapped onto the tile pool memory specified by CUarrayMapInfo::memHandle at offset CUarrayMapInfo::offset. The tile pool allocation has to be created by specifying the MEM_CREATE_USAGE_TILE_POOL flag when calling MemCreate. Also, CUarrayMapInfo::memHandleType must be set to MEM_HANDLE_TYPE_GENERIC.

If CUarrayMapInfo::memOperationType is set to MEM_OPERATION_TYPE_UNMAP then an unmapping operation is performed. CUarrayMapInfo::memHandle must be NULL.

CUarrayMapInfo::deviceBitMask specifies the list of devices that must map or unmap physical memory. Currently, this mask must have exactly one bit set, and the corresponding device must match the device associated with the stream. If CUarrayMapInfo::memOperationType is set to MEM_OPERATION_TYPE_MAP, the device must also match the device associated with the tile pool memory allocation as specified by CUarrayMapInfo::memHandle.

CUarrayMapInfo::flags and CUarrayMapInfo::reserved[] are unused and must be set to zero.

Parameters:

mapInfoList - list of CUarrayMapInfo

hStream - stream identifier for the stream to use for map or unmap operations

cuMemUnmap

public static int cuMemUnmap(long ptr,
 long size)

Unmap the backing memory of a given address range.

The range must be the entire contiguous address range that was mapped to. In other words, MemUnmap cannot unmap a sub-range of an address range mapped by MemCreate / MemMap. Any backing memory allocations will be freed if there are no existing mappings and there are no unreleased memory handles.

When MemUnmap returns successfully the address range is converted to an address reservation and can be used for a future calls to MemMap. Any new mapping to this virtual address will need to have access granted through MemSetAccess, as all mappings start with no accessibility setup.

Parameters:

ptr - starting address for the virtual address range to unmap

size - size of the virtual address range to unmap

ncuMemSetAccess

public static int ncuMemSetAccess(long ptr,
 long size,
 long desc,
 long count)

Unsafe version of: MemSetAccess

Parameters:

count - number of CUmemAccessDesc in desc

cuMemSetAccess

public static int cuMemSetAccess(long ptr,
 long size,
 CUmemAccessDesc.Buffer desc)

Set the access flags for each location specified in desc for the given virtual address range.

Given the virtual address range via ptr and size, and the locations in the array given by desc and count, set the access flags for the target locations. The range must be a fully mapped address range containing all allocations created by MemMap / MemCreate.

Parameters:

ptr - starting address for the virtual address range

size - length of the virtual address range

desc - array of CUmemAccessDesc that describe how to change the - mapping for each location specified

ncuMemGetAccess

public static int ncuMemGetAccess(long flags,
 long location,
 long ptr)

Unsafe version of: MemGetAccess

cuMemGetAccess

public static int cuMemGetAccess(LongBuffer flags,
 CUmemLocation location,
 long ptr)

Get the access flags set for the given location and ptr.

Parameters:

flags - flags set for this location

location - location in which to check the flags for

ptr - address in which to check the access flags for

ncuMemExportToShareableHandle

public static int ncuMemExportToShareableHandle(long shareableHandle,
 long handle,
 int handleType,
 long flags)

Unsafe version of: MemExportToShareableHandle

cuMemExportToShareableHandle

public static int cuMemExportToShareableHandle(ByteBuffer shareableHandle,
 long handle,
 int handleType,
 long flags)

Exports an allocation to a requested shareable handle type.

Given a CUDA memory handle, create a shareable memory allocation handle that can be used to share the memory with other processes. The recipient process can convert the shareable handle back into a CUDA memory handle using MemImportFromShareableHandle and map it with MemMap. The implementation of what this handle is and how it can be transferred is defined by the requested handle type in handleType.

Once all shareable handles are closed and the allocation is released, the allocated memory referenced will be released back to the OS and uses of the CUDA handle afterward will lead to undefined behavior.

This API can also be used in conjunction with other APIs (e.g. Vulkan, OpenGL) that support importing memory from the shareable type

Parameters:

shareableHandle - pointer to the location in which to store the requested handle type

handle - CUDA handle for the memory allocation

handleType - type of shareable handle requested (defines type and size of the shareableHandle output parameter)

flags - reserved, must be zero

cuMemExportToShareableHandle

public static int cuMemExportToShareableHandle(PointerBuffer shareableHandle,
 long handle,
 int handleType,
 long flags)

Exports an allocation to a requested shareable handle type.

Given a CUDA memory handle, create a shareable memory allocation handle that can be used to share the memory with other processes. The recipient process can convert the shareable handle back into a CUDA memory handle using MemImportFromShareableHandle and map it with MemMap. The implementation of what this handle is and how it can be transferred is defined by the requested handle type in handleType.

Once all shareable handles are closed and the allocation is released, the allocated memory referenced will be released back to the OS and uses of the CUDA handle afterward will lead to undefined behavior.

This API can also be used in conjunction with other APIs (e.g. Vulkan, OpenGL) that support importing memory from the shareable type

Parameters:

shareableHandle - pointer to the location in which to store the requested handle type

handle - CUDA handle for the memory allocation

handleType - type of shareable handle requested (defines type and size of the shareableHandle output parameter)

flags - reserved, must be zero

ncuMemImportFromShareableHandle

public static int ncuMemImportFromShareableHandle(long handle,
 long osHandle,
 int shHandleType)

Unsafe version of: MemImportFromShareableHandle

cuMemImportFromShareableHandle

public static int cuMemImportFromShareableHandle(LongBuffer handle,
 long osHandle,
 int shHandleType)

Imports an allocation from a requested shareable handle type.

If the current process cannot support the memory described by this shareable handle, this API will error as CUDA_ERROR_NOT_SUPPORTED.

Note

Importing shareable handles exported from some graphics APIs(VUlkan, OpenGL, etc) created on devices under an SLI group may not be supported, and thus this API will return CUDA_ERROR_NOT_SUPPORTED. There is no guarantee that the contents of handle will be the same CUDA memory handle for the same given OS shareable handle, or the same underlying allocation.

Parameters:

handle - CUDA Memory handle for the memory allocation

osHandle - shareable Handle representing the memory allocation that is to be imported

shHandleType - handle type of the exported handle CUmemAllocationHandleType

ncuMemGetAllocationGranularity

public static int ncuMemGetAllocationGranularity(long granularity,
 long prop,
 int option)

Unsafe version of: MemGetAllocationGranularity

cuMemGetAllocationGranularity

public static int cuMemGetAllocationGranularity(PointerBuffer granularity,
 CUmemAllocationProp prop,
 int option)

Calculates either the minimal or recommended granularity.

Calculates either the minimal or recommended granularity for a given allocation specification and returns it in granularity. This granularity can be used as a multiple for alignment, size, or address mapping.

Parameters:

granularity - returned granularity

prop - property for which to determine the granularity for

option - determines which granularity to return

ncuMemGetAllocationPropertiesFromHandle

public static int ncuMemGetAllocationPropertiesFromHandle(long prop,
 long handle)

Unsafe version of: MemGetAllocationPropertiesFromHandle

cuMemGetAllocationPropertiesFromHandle

public static int cuMemGetAllocationPropertiesFromHandle(CUmemAllocationProp prop,
 long handle)

Retrieve the contents of the property structure defining properties for this handle.

Parameters:

prop - pointer to a properties structure which will hold the information about this handle

handle - handle which to perform the query on

ncuMemRetainAllocationHandle

public static int ncuMemRetainAllocationHandle(long handle,
 long addr)

Unsafe version of: MemRetainAllocationHandle

cuMemRetainAllocationHandle

public static int cuMemRetainAllocationHandle(LongBuffer handle,
 ByteBuffer addr)

Given an address addr, returns the allocation handle of the backing memory allocation.

The handle is guaranteed to be the same handle value used to map the memory. If the address requested is not mapped, the function will fail. The returned handle must be released with corresponding number of calls to MemRelease.

Note

The address addr, can be any address in a range previously mapped by MemMap, and not necessarily the start address.

Parameters:

handle - CUDA Memory handle for the backing memory allocation

addr - memory address to query, that has been mapped previously

cuMemFreeAsync

public static int cuMemFreeAsync(long dptr,
 long hStream)

Frees memory with stream ordered semantics.

Inserts a free operation into hStream. The allocation must not be accessed after stream execution reaches the free. After this API returns, accessing the memory from any subsequent work launched on the GPU or querying its pointer attributes results in undefined behavior.

Note

During stream capture, this function results in the creation of a free node and must therefore be passed the address of a graph allocation.

Parameters:

dptr - memory to free

hStream - the stream establishing the stream ordering contract

ncuMemAllocAsync

public static int ncuMemAllocAsync(long dptr,
 long bytesize,
 long hStream)

Unsafe version of: MemAllocAsync

cuMemAllocAsync

public static int cuMemAllocAsync(PointerBuffer dptr,
 long bytesize,
 long hStream)

Allocates memory with stream ordered semantics

Inserts an allocation operation into hStream. A pointer to the allocated memory is returned immediately in *dptr. The allocation must not be accessed until the the allocation operation completes. The allocation comes from the memory pool current to the stream's device.

Note

The default memory pool of a device contains device memory from that device.

Note

Basic stream ordering allows future work submitted into the same stream to use the allocation. Stream query, stream synchronize, and CUDA events can be used to guarantee that the allocation operation completes before work submitted in a separate stream runs.

Note

During stream capture, this function results in the creation of an allocation node. In this case, the allocation is owned by the graph instead of the memory pool. The memory pool's properties are used to set the node's creation parameters.

Parameters:

dptr - returned device pointer

bytesize - number of bytes to allocate

hStream - the stream establishing the stream ordering contract and the memory pool to allocate from

cuMemPoolTrimTo

public static int cuMemPoolTrimTo(long pool,
 long minBytesToKeep)

Tries to release memory back to the OS.

Releases memory back to the OS until the pool contains fewer than minBytesToKeep reserved bytes, or there is no more memory that the allocator can safely release. The allocator cannot release OS allocations that back outstanding asynchronous allocations. The OS allocations may happen at different granularity from the user allocations.

Note

Allocations that have not been freed count as outstanding.

Note

Allocations that have been asynchronously freed but whose completion has not been observed on the host (eg. by a synchronize) can count as outstanding.

Parameters:

pool - the memory pool to trim

minBytesToKeep - if the pool has less than minBytesToKeep reserved, the TrimTo operation is a no-op. Otherwise the pool will be guaranteed to have at least minBytesToKeep bytes reserved after the operation.

ncuMemPoolSetAttribute

public static int ncuMemPoolSetAttribute(long pool,
 int attr,
 long value)

Unsafe version of: MemPoolSetAttribute

cuMemPoolSetAttribute

public static int cuMemPoolSetAttribute(long pool,
 int attr,
 ByteBuffer value)

Sets attributes of a memory pool.

Parameters:

pool - the memory pool to modify

attr - the attribute to modify. One of:

MEMPOOL_ATTR_REUSE_FOLLOW_EVENT_DEPENDENCIES	MEMPOOL_ATTR_REUSE_ALLOW_OPPORTUNISTIC
MEMPOOL_ATTR_REUSE_ALLOW_INTERNAL_DEPENDENCIES	MEMPOOL_ATTR_RELEASE_THRESHOLD
MEMPOOL_ATTR_RESERVED_MEM_CURRENT	MEMPOOL_ATTR_RESERVED_MEM_HIGH
MEMPOOL_ATTR_USED_MEM_CURRENT	MEMPOOL_ATTR_USED_MEM_HIGH

value - pointer to the value to assign

cuMemPoolSetAttribute

public static int cuMemPoolSetAttribute(long pool,
 int attr,
 IntBuffer value)

Sets attributes of a memory pool.

Parameters:

pool - the memory pool to modify

attr - the attribute to modify. One of:

MEMPOOL_ATTR_REUSE_FOLLOW_EVENT_DEPENDENCIES	MEMPOOL_ATTR_REUSE_ALLOW_OPPORTUNISTIC
MEMPOOL_ATTR_REUSE_ALLOW_INTERNAL_DEPENDENCIES	MEMPOOL_ATTR_RELEASE_THRESHOLD
MEMPOOL_ATTR_RESERVED_MEM_CURRENT	MEMPOOL_ATTR_RESERVED_MEM_HIGH
MEMPOOL_ATTR_USED_MEM_CURRENT	MEMPOOL_ATTR_USED_MEM_HIGH

value - pointer to the value to assign

cuMemPoolSetAttribute

public static int cuMemPoolSetAttribute(long pool,
 int attr,
 LongBuffer value)

Sets attributes of a memory pool.

Parameters:

pool - the memory pool to modify

attr - the attribute to modify. One of:

MEMPOOL_ATTR_REUSE_FOLLOW_EVENT_DEPENDENCIES	MEMPOOL_ATTR_REUSE_ALLOW_OPPORTUNISTIC
MEMPOOL_ATTR_REUSE_ALLOW_INTERNAL_DEPENDENCIES	MEMPOOL_ATTR_RELEASE_THRESHOLD
MEMPOOL_ATTR_RESERVED_MEM_CURRENT	MEMPOOL_ATTR_RESERVED_MEM_HIGH
MEMPOOL_ATTR_USED_MEM_CURRENT	MEMPOOL_ATTR_USED_MEM_HIGH

value - pointer to the value to assign

ncuMemPoolGetAttribute

public static int ncuMemPoolGetAttribute(long pool,
 int attr,
 long value)

Unsafe version of: MemPoolGetAttribute

cuMemPoolGetAttribute

public static int cuMemPoolGetAttribute(long pool,
 int attr,
 ByteBuffer value)

Gets attributes of a memory pool.

Parameters:

pool - the memory pool to get attributes of

attr - the attribute to get. One of:

MEMPOOL_ATTR_REUSE_FOLLOW_EVENT_DEPENDENCIES	MEMPOOL_ATTR_REUSE_ALLOW_OPPORTUNISTIC
MEMPOOL_ATTR_REUSE_ALLOW_INTERNAL_DEPENDENCIES	MEMPOOL_ATTR_RELEASE_THRESHOLD
MEMPOOL_ATTR_RESERVED_MEM_CURRENT	MEMPOOL_ATTR_RESERVED_MEM_HIGH
MEMPOOL_ATTR_USED_MEM_CURRENT	MEMPOOL_ATTR_USED_MEM_HIGH

value - retrieved value

cuMemPoolGetAttribute

public static int cuMemPoolGetAttribute(long pool,
 int attr,
 IntBuffer value)

Gets attributes of a memory pool.

Parameters:

pool - the memory pool to get attributes of

attr - the attribute to get. One of:

MEMPOOL_ATTR_REUSE_FOLLOW_EVENT_DEPENDENCIES	MEMPOOL_ATTR_REUSE_ALLOW_OPPORTUNISTIC
MEMPOOL_ATTR_REUSE_ALLOW_INTERNAL_DEPENDENCIES	MEMPOOL_ATTR_RELEASE_THRESHOLD
MEMPOOL_ATTR_RESERVED_MEM_CURRENT	MEMPOOL_ATTR_RESERVED_MEM_HIGH
MEMPOOL_ATTR_USED_MEM_CURRENT	MEMPOOL_ATTR_USED_MEM_HIGH

value - retrieved value

cuMemPoolGetAttribute

public static int cuMemPoolGetAttribute(long pool,
 int attr,
 LongBuffer value)

Gets attributes of a memory pool.

Parameters:

pool - the memory pool to get attributes of

attr - the attribute to get. One of:

MEMPOOL_ATTR_REUSE_FOLLOW_EVENT_DEPENDENCIES	MEMPOOL_ATTR_REUSE_ALLOW_OPPORTUNISTIC
MEMPOOL_ATTR_REUSE_ALLOW_INTERNAL_DEPENDENCIES	MEMPOOL_ATTR_RELEASE_THRESHOLD
MEMPOOL_ATTR_RESERVED_MEM_CURRENT	MEMPOOL_ATTR_RESERVED_MEM_HIGH
MEMPOOL_ATTR_USED_MEM_CURRENT	MEMPOOL_ATTR_USED_MEM_HIGH

value - retrieved value

ncuMemPoolSetAccess

public static int ncuMemPoolSetAccess(long pool,
 long map,
 long count)

Unsafe version of: MemPoolSetAccess

Parameters:

count - number of descriptors in the map array

cuMemPoolSetAccess

public static int cuMemPoolSetAccess(long pool,
 CUmemAccessDesc.Buffer map)

Controls visibility of pools between devices.

Parameters:

pool - the pool being modified

map - array of access descriptors. Each descriptor instructs the access to enable for a single gpu.

ncuMemPoolGetAccess

public static int ncuMemPoolGetAccess(long flags,
 long memPool,
 long location)

Unsafe version of: MemPoolGetAccess

cuMemPoolGetAccess

public static int cuMemPoolGetAccess(IntBuffer flags,
 long memPool,
 CUmemLocation location)

Returns the accessibility of a pool from a device.

Returns the accessibility of the pool's memory from the specified location.

Parameters:

flags - the accessibility of the pool from the specified location

memPool - the pool being queried

location - the location accessing the pool

ncuMemPoolCreate

public static int ncuMemPoolCreate(long pool,
 long poolProps)

Unsafe version of: MemPoolCreate

cuMemPoolCreate

public static int cuMemPoolCreate(PointerBuffer pool,
 CUmemPoolProps poolProps)

Creates a memory pool.

Creates a CUDA memory pool and returns the handle in pool. The poolProps determines the properties of the pool such as the backing device and IPC capabilities.

By default, the pool's memory will be accessible from the device it is allocated on.

Note

Specifying MEM_HANDLE_TYPE_NONE creates a memory pool that will not support IPC.

cuMemPoolDestroy

public static int cuMemPoolDestroy(long pool)

Destroys the specified memory pool.

If any pointers obtained from this pool haven't been freed or the pool has free operations that haven't completed when MemPoolDestroy is invoked, the function will return immediately and the resources associated with the pool will be released automatically once there are no more outstanding allocations.

Destroying the current mempool of a device sets the default mempool of that device as the current mempool for that device.

Note

A device's default memory pool cannot be destroyed.

ncuMemAllocFromPoolAsync

public static int ncuMemAllocFromPoolAsync(long dptr,
 long bytesize,
 long pool,
 long hStream)

Unsafe version of: MemAllocFromPoolAsync

cuMemAllocFromPoolAsync

public static int cuMemAllocFromPoolAsync(PointerBuffer dptr,
 long bytesize,
 long pool,
 long hStream)

Allocates memory from a specified pool with stream ordered semantics.

Inserts an allocation operation into hStream. A pointer to the allocated memory is returned immediately in *dptr. The allocation must not be accessed until the the allocation operation completes. The allocation comes from the specified memory pool.

Note

The specified memory pool may be from a device different than that of the specified hStream.

• Basic stream ordering allows future work submitted into the same stream to use the allocation. Stream query, stream synchronize, and CUDA events can be used to guarantee that the allocation operation completes before work submitted in a separate stream runs.

Note

During stream capture, this function results in the creation of an allocation node. In this case, the allocation is owned by the graph instead of the memory pool. The memory pool's properties are used to set the node's creation parameters.

Parameters:

dptr - returned device pointer

bytesize - number of bytes to allocate

pool - the pool to allocate from

hStream - the stream establishing the stream ordering semantic

ncuMemPoolExportToShareableHandle

public static int ncuMemPoolExportToShareableHandle(long handle_out,
 long pool,
 int handleType,
 long flags)

Unsafe version of: MemPoolExportToShareableHandle

cuMemPoolExportToShareableHandle

public static int cuMemPoolExportToShareableHandle(ByteBuffer handle_out,
 long pool,
 int handleType,
 long flags)

Exports a memory pool to the requested handle type.

Given an IPC capable mempool, create an OS handle to share the pool with another process. A recipient process can convert the shareable handle into a mempool with MemPoolImportFromShareableHandle. Individual pointers can then be shared with the MemPoolExportPointer and MemPoolImportPointer APIs. The implementation of what the shareable handle is and how it can be transferred is defined by the requested handle type.

Note

To create an IPC capable mempool, create a mempool with a CUmemAllocationHandleType other than MEM_HANDLE_TYPE_NONE.

Parameters:

handle_out - returned OS handle

pool - pool to export

handleType - the type of handle to create

flags - must be 0

cuMemPoolExportToShareableHandle

public static int cuMemPoolExportToShareableHandle(PointerBuffer handle_out,
 long pool,
 int handleType,
 long flags)

Exports a memory pool to the requested handle type.

Given an IPC capable mempool, create an OS handle to share the pool with another process. A recipient process can convert the shareable handle into a mempool with MemPoolImportFromShareableHandle. Individual pointers can then be shared with the MemPoolExportPointer and MemPoolImportPointer APIs. The implementation of what the shareable handle is and how it can be transferred is defined by the requested handle type.

Note

To create an IPC capable mempool, create a mempool with a CUmemAllocationHandleType other than MEM_HANDLE_TYPE_NONE.

Parameters:

handle_out - returned OS handle

pool - pool to export

handleType - the type of handle to create

flags - must be 0

ncuMemPoolImportFromShareableHandle

public static int ncuMemPoolImportFromShareableHandle(long pool_out,
 long handle,
 int handleType,
 long flags)

Unsafe version of: MemPoolImportFromShareableHandle

cuMemPoolImportFromShareableHandle

public static int cuMemPoolImportFromShareableHandle(PointerBuffer pool_out,
 ByteBuffer handle,
 int handleType,
 long flags)

Imports a memory pool from a shared handle.

Specific allocations can be imported from the imported pool with MemPoolImportPointer.

Note

Imported memory pools do not support creating new allocations. As such imported memory pools may not be used in DeviceSetMemPool or MemAllocFromPoolAsync calls.

Parameters:

pool_out - returned memory pool

handle - OS handle of the pool to open

handleType - the type of handle being imported

flags - must be 0

cuMemPoolImportFromShareableHandle

public static int cuMemPoolImportFromShareableHandle(PointerBuffer pool_out,
 PointerBuffer handle,
 int handleType,
 long flags)

Imports a memory pool from a shared handle.

Specific allocations can be imported from the imported pool with MemPoolImportPointer.

Note

Imported memory pools do not support creating new allocations. As such imported memory pools may not be used in DeviceSetMemPool or MemAllocFromPoolAsync calls.

Parameters:

pool_out - returned memory pool

handle - OS handle of the pool to open

handleType - the type of handle being imported

flags - must be 0

ncuMemPoolExportPointer

public static int ncuMemPoolExportPointer(long shareData_out,
 long ptr)

Unsafe version of: MemPoolExportPointer

cuMemPoolExportPointer

public static int cuMemPoolExportPointer(CUmemPoolPtrExportData shareData_out,
 long ptr)

Export data to share a memory pool allocation between processes.

Constructs shareData_out for sharing a specific allocation from an already shared memory pool. The recipient process can import the allocation with the MemPoolImportPointer api. The data is not a handle and may be shared through any IPC mechanism.

Parameters:

shareData_out - returned export data

ptr - pointer to memory being exported

ncuMemPoolImportPointer

public static int ncuMemPoolImportPointer(long ptr_out,
 long pool,
 long shareData)

Unsafe version of: MemPoolImportPointer

cuMemPoolImportPointer

public static int cuMemPoolImportPointer(PointerBuffer ptr_out,
 long pool,
 CUmemPoolPtrExportData shareData)

Import a memory pool allocation from another process.

Returns in ptr_out a pointer to the imported memory. The imported memory must not be accessed before the allocation operation completes in the exporting process. The imported memory must be freed from all importing processes before being freed in the exporting process. The pointer may be freed with MemFree or MemFreeAsync. If cuMemFreeAsync is used, the free must be completed on the importing process before the free operation on the exporting process.

Note

The cuMemFreeAsync api may be used in the exporting process before the cuMemFreeAsync operation completes in its stream as long as the cuMemFreeAsync in the exporting process specifies a stream with a stream dependency on the importing process's cuMemFreeAsync.

Parameters:

ptr_out - pointer to imported memory

pool - pool from which to import

shareData - data specifying the memory to import

ncuPointerGetAttribute

public static int ncuPointerGetAttribute(long data,
 int attribute,
 long ptr)

Unsafe version of: PointerGetAttribute

cuPointerGetAttribute

public static int cuPointerGetAttribute(ByteBuffer data,
 int attribute,
 long ptr)

Returns information about a pointer.

The supported attributes are:

• POINTER_ATTRIBUTE_CONTEXT: Returns in *data the CUcontext in which ptr was allocated or registered. The type of data must be CUcontext *.

  If ptr was not allocated by, mapped by, or registered with a CUcontext which uses unified virtual addressing then CUDA_ERROR_INVALID_VALUE is returned.

• POINTER_ATTRIBUTE_MEMORY_TYPE:

  Returns in *data the physical memory type of the memory that ptr addresses as a CUmemorytype enumerated value. The type of data must be unsigned int.

  If ptr addresses device memory then *data is set to MEMORYTYPE_DEVICE. The particular CUdevice on which the memory resides is the CUdevice of the CUcontext returned by the POINTER_ATTRIBUTE_CONTEXT attribute of ptr.

  If ptr addresses host memory then *data is set to MEMORYTYPE_HOST.

  If ptr was not allocated by, mapped by, or registered with a CUcontext which uses unified virtual addressing then CUDA_ERROR_INVALID_VALUE is returned.

  If the current CUcontext does not support unified virtual addressing then CUDA_ERROR_INVALID_CONTEXT is returned.

• POINTER_ATTRIBUTE_DEVICE_POINTER: Returns in *data the device pointer value through which ptr may be accessed by kernels running in the current CUcontext. The type of data must be CUdeviceptr *.

  If there exists no device pointer value through which kernels running in the current CUcontext may access ptr then CUDA_ERROR_INVALID_VALUE is returned.

  If there is no current CUcontext then CUDA_ERROR_INVALID_CONTEXT is returned.

  Except in the exceptional disjoint addressing cases discussed below, the value returned in *data will equal the input value ptr.

• POINTER_ATTRIBUTE_HOST_POINTER: Returns in *data the host pointer value through which ptr may be accessed by by the host program. The type of data must be void **. If there exists no host pointer value through which the host program may directly access ptr then CUDA_ERROR_INVALID_VALUE is returned.

  Except in the exceptional disjoint addressing cases discussed below, the value returned in *data will equal the input value ptr.

• POINTER_ATTRIBUTE_P2P_TOKENS: Returns in *data two tokens for use with the nv-p2p.h Linux kernel interface. data must be a struct of type CUDA_POINTER_ATTRIBUTE_P2P_TOKENS.

  ptr must be a pointer to memory obtained from MemAlloc. Note that p2pToken and vaSpaceToken are only valid for the lifetime of the source allocation. A subsequent allocation at the same address may return completely different tokens. Querying this attribute has a side effect of setting the attribute POINTER_ATTRIBUTE_SYNC_MEMOPS for the region of memory that ptr points to.

• POINTER_ATTRIBUTE_SYNC_MEMOPS:

  A boolean attribute which when set, ensures that synchronous memory operations initiated on the region of memory that ptr points to will always synchronize. See further documentation in the section titled "API synchronization behavior" to learn more about cases when synchronous memory operations can exhibit asynchronous behavior.

• POINTER_ATTRIBUTE_BUFFER_ID: Returns in *data a buffer ID which is guaranteed to be unique within the process. data must point to an unsigned long long.

  ptr must be a pointer to memory obtained from a CUDA memory allocation API. Every memory allocation from any of the CUDA memory allocation APIs will have a unique ID over a process lifetime. Subsequent allocations do not reuse IDs from previous freed allocations. IDs are only unique within a single process.

• POINTER_ATTRIBUTE_IS_MANAGED: Returns in *data a boolean that indicates whether the pointer points to managed memory or not.

  If ptr is not a valid CUDA pointer then CUDA_ERROR_INVALID_VALUE is returned.

• POINTER_ATTRIBUTE_DEVICE_ORDINAL: Returns in *data an integer representing a device ordinal of a device against which the memory was allocated or registered.
• POINTER_ATTRIBUTE_IS_LEGACY_CUDA_IPC_CAPABLE: Returns in *data a boolean that indicates if this pointer maps to an allocation that is suitable for cudaIpcGetMemHandle().
• POINTER_ATTRIBUTE_RANGE_START_ADDR: Returns in *data the starting address for the allocation referenced by the device pointer ptr. Note that this is not necessarily the address of the mapped region, but the address of the mappable address range ptr references (e.g. from MemAddressReserve).
• POINTER_ATTRIBUTE_RANGE_SIZE: Returns in *data the size for the allocation referenced by the device pointer ptr. Note that this is not necessarily the size of the mapped region, but the size of the mappable address range ptr references (e.g. from MemAddressReserve). To retrieve the size of the mapped region, see MemGetAddressRange.
• POINTER_ATTRIBUTE_MAPPED: Returns in *data a boolean that indicates if this pointer is in a valid address range that is mapped to a backing allocation.
• POINTER_ATTRIBUTE_ALLOWED_HANDLE_TYPES: Returns a bitmask of the allowed handle types for an allocation that may be passed to MemExportToShareableHandle.
• POINTER_ATTRIBUTE_MEMPOOL_HANDLE: Returns in *data the handle to the mempool that the allocation was obtained from.

Note that for most allocations in the unified virtual address space the host and device pointer for accessing the allocation will be the same. The exceptions to this are - user memory registered using MemHostRegister - host memory allocated using MemHostAlloc with the MEMHOSTALLOC_WRITECOMBINED flag For these types of allocation there will exist separate, disjoint host and device addresses for accessing the allocation. In particular

• The host address will correspond to an invalid unmapped device address (which will result in an exception if accessed from the device)
• The device address will correspond to an invalid unmapped host address (which will result in an exception if accessed from the host).

For these types of allocations, querying POINTER_ATTRIBUTE_HOST_POINTER and POINTER_ATTRIBUTE_DEVICE_POINTER may be used to retrieve the host and device addresses from either address.

Parameters:

data - returned pointer attribute value

attribute - pointer attribute to query

ptr - pointer

cuPointerGetAttribute

public static int cuPointerGetAttribute(PointerBuffer data,
 int attribute,
 long ptr)

Returns information about a pointer.

The supported attributes are:

• POINTER_ATTRIBUTE_CONTEXT: Returns in *data the CUcontext in which ptr was allocated or registered. The type of data must be CUcontext *.

  If ptr was not allocated by, mapped by, or registered with a CUcontext which uses unified virtual addressing then CUDA_ERROR_INVALID_VALUE is returned.

• POINTER_ATTRIBUTE_MEMORY_TYPE:

  Returns in *data the physical memory type of the memory that ptr addresses as a CUmemorytype enumerated value. The type of data must be unsigned int.

  If ptr addresses device memory then *data is set to MEMORYTYPE_DEVICE. The particular CUdevice on which the memory resides is the CUdevice of the CUcontext returned by the POINTER_ATTRIBUTE_CONTEXT attribute of ptr.

  If ptr addresses host memory then *data is set to MEMORYTYPE_HOST.

  If ptr was not allocated by, mapped by, or registered with a CUcontext which uses unified virtual addressing then CUDA_ERROR_INVALID_VALUE is returned.

  If the current CUcontext does not support unified virtual addressing then CUDA_ERROR_INVALID_CONTEXT is returned.

• POINTER_ATTRIBUTE_DEVICE_POINTER: Returns in *data the device pointer value through which ptr may be accessed by kernels running in the current CUcontext. The type of data must be CUdeviceptr *.

  If there exists no device pointer value through which kernels running in the current CUcontext may access ptr then CUDA_ERROR_INVALID_VALUE is returned.

  If there is no current CUcontext then CUDA_ERROR_INVALID_CONTEXT is returned.

  Except in the exceptional disjoint addressing cases discussed below, the value returned in *data will equal the input value ptr.

• POINTER_ATTRIBUTE_HOST_POINTER: Returns in *data the host pointer value through which ptr may be accessed by by the host program. The type of data must be void **. If there exists no host pointer value through which the host program may directly access ptr then CUDA_ERROR_INVALID_VALUE is returned.

  Except in the exceptional disjoint addressing cases discussed below, the value returned in *data will equal the input value ptr.

• POINTER_ATTRIBUTE_P2P_TOKENS: Returns in *data two tokens for use with the nv-p2p.h Linux kernel interface. data must be a struct of type CUDA_POINTER_ATTRIBUTE_P2P_TOKENS.

  ptr must be a pointer to memory obtained from MemAlloc. Note that p2pToken and vaSpaceToken are only valid for the lifetime of the source allocation. A subsequent allocation at the same address may return completely different tokens. Querying this attribute has a side effect of setting the attribute POINTER_ATTRIBUTE_SYNC_MEMOPS for the region of memory that ptr points to.

• POINTER_ATTRIBUTE_SYNC_MEMOPS:

  A boolean attribute which when set, ensures that synchronous memory operations initiated on the region of memory that ptr points to will always synchronize. See further documentation in the section titled "API synchronization behavior" to learn more about cases when synchronous memory operations can exhibit asynchronous behavior.

• POINTER_ATTRIBUTE_BUFFER_ID: Returns in *data a buffer ID which is guaranteed to be unique within the process. data must point to an unsigned long long.

  ptr must be a pointer to memory obtained from a CUDA memory allocation API. Every memory allocation from any of the CUDA memory allocation APIs will have a unique ID over a process lifetime. Subsequent allocations do not reuse IDs from previous freed allocations. IDs are only unique within a single process.

• POINTER_ATTRIBUTE_IS_MANAGED: Returns in *data a boolean that indicates whether the pointer points to managed memory or not.

  If ptr is not a valid CUDA pointer then CUDA_ERROR_INVALID_VALUE is returned.

• POINTER_ATTRIBUTE_DEVICE_ORDINAL: Returns in *data an integer representing a device ordinal of a device against which the memory was allocated or registered.
• POINTER_ATTRIBUTE_IS_LEGACY_CUDA_IPC_CAPABLE: Returns in *data a boolean that indicates if this pointer maps to an allocation that is suitable for cudaIpcGetMemHandle().
• POINTER_ATTRIBUTE_RANGE_START_ADDR: Returns in *data the starting address for the allocation referenced by the device pointer ptr. Note that this is not necessarily the address of the mapped region, but the address of the mappable address range ptr references (e.g. from MemAddressReserve).
• POINTER_ATTRIBUTE_RANGE_SIZE: Returns in *data the size for the allocation referenced by the device pointer ptr. Note that this is not necessarily the size of the mapped region, but the size of the mappable address range ptr references (e.g. from MemAddressReserve). To retrieve the size of the mapped region, see MemGetAddressRange.
• POINTER_ATTRIBUTE_MAPPED: Returns in *data a boolean that indicates if this pointer is in a valid address range that is mapped to a backing allocation.
• POINTER_ATTRIBUTE_ALLOWED_HANDLE_TYPES: Returns a bitmask of the allowed handle types for an allocation that may be passed to MemExportToShareableHandle.
• POINTER_ATTRIBUTE_MEMPOOL_HANDLE: Returns in *data the handle to the mempool that the allocation was obtained from.

Note that for most allocations in the unified virtual address space the host and device pointer for accessing the allocation will be the same. The exceptions to this are - user memory registered using MemHostRegister - host memory allocated using MemHostAlloc with the MEMHOSTALLOC_WRITECOMBINED flag For these types of allocation there will exist separate, disjoint host and device addresses for accessing the allocation. In particular

• The host address will correspond to an invalid unmapped device address (which will result in an exception if accessed from the device)
• The device address will correspond to an invalid unmapped host address (which will result in an exception if accessed from the host).

For these types of allocations, querying POINTER_ATTRIBUTE_HOST_POINTER and POINTER_ATTRIBUTE_DEVICE_POINTER may be used to retrieve the host and device addresses from either address.

Parameters:

data - returned pointer attribute value

attribute - pointer attribute to query

ptr - pointer

cuPointerGetAttribute

public static int cuPointerGetAttribute(IntBuffer data,
 int attribute,
 long ptr)

Returns information about a pointer.

The supported attributes are:

• POINTER_ATTRIBUTE_CONTEXT: Returns in *data the CUcontext in which ptr was allocated or registered. The type of data must be CUcontext *.

  If ptr was not allocated by, mapped by, or registered with a CUcontext which uses unified virtual addressing then CUDA_ERROR_INVALID_VALUE is returned.

• POINTER_ATTRIBUTE_MEMORY_TYPE:

  Returns in *data the physical memory type of the memory that ptr addresses as a CUmemorytype enumerated value. The type of data must be unsigned int.

  If ptr addresses device memory then *data is set to MEMORYTYPE_DEVICE. The particular CUdevice on which the memory resides is the CUdevice of the CUcontext returned by the POINTER_ATTRIBUTE_CONTEXT attribute of ptr.

  If ptr addresses host memory then *data is set to MEMORYTYPE_HOST.

  If ptr was not allocated by, mapped by, or registered with a CUcontext which uses unified virtual addressing then CUDA_ERROR_INVALID_VALUE is returned.

  If the current CUcontext does not support unified virtual addressing then CUDA_ERROR_INVALID_CONTEXT is returned.

• POINTER_ATTRIBUTE_DEVICE_POINTER: Returns in *data the device pointer value through which ptr may be accessed by kernels running in the current CUcontext. The type of data must be CUdeviceptr *.

  If there exists no device pointer value through which kernels running in the current CUcontext may access ptr then CUDA_ERROR_INVALID_VALUE is returned.

  If there is no current CUcontext then CUDA_ERROR_INVALID_CONTEXT is returned.

  Except in the exceptional disjoint addressing cases discussed below, the value returned in *data will equal the input value ptr.

• POINTER_ATTRIBUTE_HOST_POINTER: Returns in *data the host pointer value through which ptr may be accessed by by the host program. The type of data must be void **. If there exists no host pointer value through which the host program may directly access ptr then CUDA_ERROR_INVALID_VALUE is returned.

  Except in the exceptional disjoint addressing cases discussed below, the value returned in *data will equal the input value ptr.

• POINTER_ATTRIBUTE_P2P_TOKENS: Returns in *data two tokens for use with the nv-p2p.h Linux kernel interface. data must be a struct of type CUDA_POINTER_ATTRIBUTE_P2P_TOKENS.

  ptr must be a pointer to memory obtained from MemAlloc. Note that p2pToken and vaSpaceToken are only valid for the lifetime of the source allocation. A subsequent allocation at the same address may return completely different tokens. Querying this attribute has a side effect of setting the attribute POINTER_ATTRIBUTE_SYNC_MEMOPS for the region of memory that ptr points to.

• POINTER_ATTRIBUTE_SYNC_MEMOPS:

  A boolean attribute which when set, ensures that synchronous memory operations initiated on the region of memory that ptr points to will always synchronize. See further documentation in the section titled "API synchronization behavior" to learn more about cases when synchronous memory operations can exhibit asynchronous behavior.

• POINTER_ATTRIBUTE_BUFFER_ID: Returns in *data a buffer ID which is guaranteed to be unique within the process. data must point to an unsigned long long.

  ptr must be a pointer to memory obtained from a CUDA memory allocation API. Every memory allocation from any of the CUDA memory allocation APIs will have a unique ID over a process lifetime. Subsequent allocations do not reuse IDs from previous freed allocations. IDs are only unique within a single process.

• POINTER_ATTRIBUTE_IS_MANAGED: Returns in *data a boolean that indicates whether the pointer points to managed memory or not.

  If ptr is not a valid CUDA pointer then CUDA_ERROR_INVALID_VALUE is returned.

• POINTER_ATTRIBUTE_DEVICE_ORDINAL: Returns in *data an integer representing a device ordinal of a device against which the memory was allocated or registered.
• POINTER_ATTRIBUTE_IS_LEGACY_CUDA_IPC_CAPABLE: Returns in *data a boolean that indicates if this pointer maps to an allocation that is suitable for cudaIpcGetMemHandle().
• POINTER_ATTRIBUTE_RANGE_START_ADDR: Returns in *data the starting address for the allocation referenced by the device pointer ptr. Note that this is not necessarily the address of the mapped region, but the address of the mappable address range ptr references (e.g. from MemAddressReserve).
• POINTER_ATTRIBUTE_RANGE_SIZE: Returns in *data the size for the allocation referenced by the device pointer ptr. Note that this is not necessarily the size of the mapped region, but the size of the mappable address range ptr references (e.g. from MemAddressReserve). To retrieve the size of the mapped region, see MemGetAddressRange.
• POINTER_ATTRIBUTE_MAPPED: Returns in *data a boolean that indicates if this pointer is in a valid address range that is mapped to a backing allocation.
• POINTER_ATTRIBUTE_ALLOWED_HANDLE_TYPES: Returns a bitmask of the allowed handle types for an allocation that may be passed to MemExportToShareableHandle.
• POINTER_ATTRIBUTE_MEMPOOL_HANDLE: Returns in *data the handle to the mempool that the allocation was obtained from.

Note that for most allocations in the unified virtual address space the host and device pointer for accessing the allocation will be the same. The exceptions to this are - user memory registered using MemHostRegister - host memory allocated using MemHostAlloc with the MEMHOSTALLOC_WRITECOMBINED flag For these types of allocation there will exist separate, disjoint host and device addresses for accessing the allocation. In particular

• The host address will correspond to an invalid unmapped device address (which will result in an exception if accessed from the device)
• The device address will correspond to an invalid unmapped host address (which will result in an exception if accessed from the host).

For these types of allocations, querying POINTER_ATTRIBUTE_HOST_POINTER and POINTER_ATTRIBUTE_DEVICE_POINTER may be used to retrieve the host and device addresses from either address.

Parameters:

data - returned pointer attribute value

attribute - pointer attribute to query

ptr - pointer

cuPointerGetAttribute

public static int cuPointerGetAttribute(LongBuffer data,
 int attribute,
 long ptr)

Returns information about a pointer.

The supported attributes are:

• POINTER_ATTRIBUTE_CONTEXT: Returns in *data the CUcontext in which ptr was allocated or registered. The type of data must be CUcontext *.

  If ptr was not allocated by, mapped by, or registered with a CUcontext which uses unified virtual addressing then CUDA_ERROR_INVALID_VALUE is returned.

• POINTER_ATTRIBUTE_MEMORY_TYPE:

  Returns in *data the physical memory type of the memory that ptr addresses as a CUmemorytype enumerated value. The type of data must be unsigned int.

  If ptr addresses device memory then *data is set to MEMORYTYPE_DEVICE. The particular CUdevice on which the memory resides is the CUdevice of the CUcontext returned by the POINTER_ATTRIBUTE_CONTEXT attribute of ptr.

  If ptr addresses host memory then *data is set to MEMORYTYPE_HOST.

  If ptr was not allocated by, mapped by, or registered with a CUcontext which uses unified virtual addressing then CUDA_ERROR_INVALID_VALUE is returned.

  If the current CUcontext does not support unified virtual addressing then CUDA_ERROR_INVALID_CONTEXT is returned.

• POINTER_ATTRIBUTE_DEVICE_POINTER: Returns in *data the device pointer value through which ptr may be accessed by kernels running in the current CUcontext. The type of data must be CUdeviceptr *.

  If there exists no device pointer value through which kernels running in the current CUcontext may access ptr then CUDA_ERROR_INVALID_VALUE is returned.

  If there is no current CUcontext then CUDA_ERROR_INVALID_CONTEXT is returned.

  Except in the exceptional disjoint addressing cases discussed below, the value returned in *data will equal the input value ptr.

• POINTER_ATTRIBUTE_HOST_POINTER: Returns in *data the host pointer value through which ptr may be accessed by by the host program. The type of data must be void **. If there exists no host pointer value through which the host program may directly access ptr then CUDA_ERROR_INVALID_VALUE is returned.

  Except in the exceptional disjoint addressing cases discussed below, the value returned in *data will equal the input value ptr.

• POINTER_ATTRIBUTE_P2P_TOKENS: Returns in *data two tokens for use with the nv-p2p.h Linux kernel interface. data must be a struct of type CUDA_POINTER_ATTRIBUTE_P2P_TOKENS.

  ptr must be a pointer to memory obtained from MemAlloc. Note that p2pToken and vaSpaceToken are only valid for the lifetime of the source allocation. A subsequent allocation at the same address may return completely different tokens. Querying this attribute has a side effect of setting the attribute POINTER_ATTRIBUTE_SYNC_MEMOPS for the region of memory that ptr points to.

• POINTER_ATTRIBUTE_SYNC_MEMOPS:

  A boolean attribute which when set, ensures that synchronous memory operations initiated on the region of memory that ptr points to will always synchronize. See further documentation in the section titled "API synchronization behavior" to learn more about cases when synchronous memory operations can exhibit asynchronous behavior.

• POINTER_ATTRIBUTE_BUFFER_ID: Returns in *data a buffer ID which is guaranteed to be unique within the process. data must point to an unsigned long long.

  ptr must be a pointer to memory obtained from a CUDA memory allocation API. Every memory allocation from any of the CUDA memory allocation APIs will have a unique ID over a process lifetime. Subsequent allocations do not reuse IDs from previous freed allocations. IDs are only unique within a single process.

• POINTER_ATTRIBUTE_IS_MANAGED: Returns in *data a boolean that indicates whether the pointer points to managed memory or not.

  If ptr is not a valid CUDA pointer then CUDA_ERROR_INVALID_VALUE is returned.

• POINTER_ATTRIBUTE_DEVICE_ORDINAL: Returns in *data an integer representing a device ordinal of a device against which the memory was allocated or registered.
• POINTER_ATTRIBUTE_IS_LEGACY_CUDA_IPC_CAPABLE: Returns in *data a boolean that indicates if this pointer maps to an allocation that is suitable for cudaIpcGetMemHandle().
• POINTER_ATTRIBUTE_RANGE_START_ADDR: Returns in *data the starting address for the allocation referenced by the device pointer ptr. Note that this is not necessarily the address of the mapped region, but the address of the mappable address range ptr references (e.g. from MemAddressReserve).
• POINTER_ATTRIBUTE_RANGE_SIZE: Returns in *data the size for the allocation referenced by the device pointer ptr. Note that this is not necessarily the size of the mapped region, but the size of the mappable address range ptr references (e.g. from MemAddressReserve). To retrieve the size of the mapped region, see MemGetAddressRange.
• POINTER_ATTRIBUTE_MAPPED: Returns in *data a boolean that indicates if this pointer is in a valid address range that is mapped to a backing allocation.
• POINTER_ATTRIBUTE_ALLOWED_HANDLE_TYPES: Returns a bitmask of the allowed handle types for an allocation that may be passed to MemExportToShareableHandle.
• POINTER_ATTRIBUTE_MEMPOOL_HANDLE: Returns in *data the handle to the mempool that the allocation was obtained from.

Note that for most allocations in the unified virtual address space the host and device pointer for accessing the allocation will be the same. The exceptions to this are - user memory registered using MemHostRegister - host memory allocated using MemHostAlloc with the MEMHOSTALLOC_WRITECOMBINED flag For these types of allocation there will exist separate, disjoint host and device addresses for accessing the allocation. In particular

• The host address will correspond to an invalid unmapped device address (which will result in an exception if accessed from the device)
• The device address will correspond to an invalid unmapped host address (which will result in an exception if accessed from the host).

For these types of allocations, querying POINTER_ATTRIBUTE_HOST_POINTER and POINTER_ATTRIBUTE_DEVICE_POINTER may be used to retrieve the host and device addresses from either address.

Parameters:

data - returned pointer attribute value

attribute - pointer attribute to query

ptr - pointer

cuMemPrefetchAsync

public static int cuMemPrefetchAsync(long devPtr,
 long count,
 int dstDevice,
 long hStream)

Prefetches memory to the specified destination device,

Prefetches memory to the specified destination device. devPtr is the base device pointer of the memory to be prefetched and dstDevice is the destination device. count specifies the number of bytes to copy. hStream is the stream in which the operation is enqueued. The memory range must refer to managed memory allocated via MemAllocManaged or declared via __managed__ variables.

Passing in DEVICE_CPU for dstDevice will prefetch the data to host memory. If dstDevice is a GPU, then the device attribute DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS must be non-zero. Additionally, hStream must be associated with a device that has a non-zero value for the device attribute DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS.

The start address and end address of the memory range will be rounded down and rounded up respectively to be aligned to CPU page size before the prefetch operation is enqueued in the stream.

If no physical memory has been allocated for this region, then this memory region will be populated and mapped on the destination device. If there's insufficient memory to prefetch the desired region, the Unified Memory driver may evict pages from other MemAllocManaged allocations to host memory in order to make room. Device memory allocated using MemAlloc or ArrayCreate will not be evicted.

By default, any mappings to the previous location of the migrated pages are removed and mappings for the new location are only setup on dstDevice. The exact behavior however also depends on the settings applied to this memory range via MemAdvise as described below:

If MEM_ADVISE_SET_READ_MOSTLY was set on any subset of this memory range, then that subset will create a read-only copy of the pages on dstDevice.

If MEM_ADVISE_SET_PREFERRED_LOCATION was called on any subset of this memory range, then the pages will be migrated to dstDevice even if dstDevice is not the preferred location of any pages in the memory range.

If MEM_ADVISE_SET_ACCESSED_BY was called on any subset of this memory range, then mappings to those pages from all the appropriate processors are updated to refer to the new location if establishing such a mapping is possible. Otherwise, those mappings are cleared.

Note that this API is not required for functionality and only serves to improve performance by allowing the application to migrate data to a suitable location before it is accessed. Memory accesses to this range are always coherent and are allowed even when the data is actively being migrated.

Note that this function is asynchronous with respect to the host and all work on other devices.

Parameters:

devPtr - pointer to be prefetched

count - size in bytes

dstDevice - destination device to prefetch to

hStream - stream to enqueue prefetch operation

cuMemAdvise

public static int cuMemAdvise(long devPtr,
 long count,
 int advice,
 int device)

Advise about the usage of a given memory range.

Advise the Unified Memory subsystem about the usage pattern for the memory range starting at devPtr with a size of count bytes. The start address and end address of the memory range will be rounded down and rounded up respectively to be aligned to CPU page size before the advice is applied. The memory range must refer to managed memory allocated via MemAllocManaged or declared via __managed__ variables. The memory range could also refer to system-allocated pageable memory provided it represents a valid, host-accessible region of memory and all additional constraints imposed by advice as outlined below are also satisfied. Specifying an invalid system-allocated pageable memory range results in an error being returned.

The advice parameter can take the following values:

• MEM_ADVISE_SET_READ_MOSTLY: This implies that the data is mostly going to be read from and only occasionally written to. Any read accesses from any processor to this region will create a read-only copy of at least the accessed pages in that processor's memory. Additionally, if MemPrefetchAsync is called on this region, it will create a read-only copy of the data on the destination processor. If any processor writes to this region, all copies of the corresponding page will be invalidated except for the one where the write occurred. The device argument is ignored for this advice. Note that for a page to be read-duplicated, the accessing processor must either be the CPU or a GPU that has a non-zero value for the device attribute DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS. Also, if a context is created on a device that does not have the device attribute DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS set, then read-duplication will not occur until all such contexts are destroyed. If the memory region refers to valid system-allocated pageable memory, then the accessing device must have a non-zero value for the device attribute DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS for a read-only copy to be created on that device. Note however that if the accessing device also has a non-zero value for the device attribute DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES, then setting this advice will not create a read-only copy when that device accesses this memory region.
• MEM_ADVISE_UNSET_READ_MOSTLY: Undoes the effect of MEM_ADVISE_SET_READ_MOSTLY and also prevents the Unified Memory driver from attempting heuristic read-duplication on the memory range. Any read-duplicated copies of the data will be collapsed into a single copy. The location for the collapsed copy will be the preferred location if the page has a preferred location and one of the read-duplicated copies was resident at that location. Otherwise, the location chosen is arbitrary.
• MEM_ADVISE_SET_PREFERRED_LOCATION: This advice sets the preferred location for the data to be the memory belonging to device. Passing in CU_DEVICE_CPU for device sets the preferred location as host memory. If device is a GPU, then it must have a non-zero value for the device attribute DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS. Setting the preferred location does not cause data to migrate to that location immediately. Instead, it guides the migration policy when a fault occurs on that memory region. If the data is already in its preferred location and the faulting processor can establish a mapping without requiring the data to be migrated, then data migration will be avoided. On the other hand, if the data is not in its preferred location or if a direct mapping cannot be established, then it will be migrated to the processor accessing it. It is important to note that setting the preferred location does not prevent data prefetching done using MemPrefetchAsync. Having a preferred location can override the page thrash detection and resolution logic in the Unified Memory driver. Normally, if a page is detected to be constantly thrashing between for example host and device memory, the page may eventually be pinned to host memory by the Unified Memory driver. But if the preferred location is set as device memory, then the page will continue to thrash indefinitely. If MEM_ADVISE_SET_READ_MOSTLY is also set on this memory region or any subset of it, then the policies associated with that advice will override the policies of this advice, unless read accesses from device will not result in a read-only copy being created on that device as outlined in description for the advice MEM_ADVISE_SET_READ_MOSTLY. If the memory region refers to valid system-allocated pageable memory, then device must have a non-zero value for the device attribute DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS. Additionally, if device has a non-zero value for the device attribute DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES, then this call has no effect. Note however that this behavior may change in the future.
• MEM_ADVISE_UNSET_PREFERRED_LOCATION: Undoes the effect of MEM_ADVISE_SET_PREFERRED_LOCATION and changes the preferred location to none.
• MEM_ADVISE_SET_ACCESSED_BY: This advice implies that the data will be accessed by device. Passing in DEVICE_CPU for device will set the advice for the CPU. If device is a GPU, then the device attribute DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS must be non-zero. This advice does not cause data migration and has no impact on the location of the data per se. Instead, it causes the data to always be mapped in the specified processor's page tables, as long as the location of the data permits a mapping to be established. If the data gets migrated for any reason, the mappings are updated accordingly. This advice is recommended in scenarios where data locality is not important, but avoiding faults is. Consider for example a system containing multiple GPUs with peer-to-peer access enabled, where the data located on one GPU is occasionally accessed by peer GPUs. In such scenarios, migrating data over to the other GPUs is not as important because the accesses are infrequent and the overhead of migration may be too high. But preventing faults can still help improve performance, and so having a mapping set up in advance is useful. Note that on CPU access of this data, the data may be migrated to host memory because the CPU typically cannot access device memory directly. Any GPU that had the MEM_ADVISE_SET_ACCESSED_BY flag set for this data will now have its mapping updated to point to the page in host memory. If MEM_ADVISE_SET_READ_MOSTLY is also set on this memory region or any subset of it, then the policies associated with that advice will override the policies of this advice. Additionally, if the preferred location of this memory region or any subset of it is also device, then the policies associated with MEM_ADVISE_SET_PREFERRED_LOCATION will override the policies of this advice. If the memory region refers to valid system-allocated pageable memory, then device must have a non-zero value for the device attribute DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS. Additionally, if device has a non-zero value for the device attribute DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES, then this call has no effect.
• MEM_ADVISE_UNSET_ACCESSED_BY: Undoes the effect of MEM_ADVISE_SET_ACCESSED_BY. Any mappings to the data from device may be removed at any time causing accesses to result in non-fatal page faults. If the memory region refers to valid system-allocated pageable memory, then device must have a non-zero value for the device attribute DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS. Additionally, if device has a non-zero value for the device attribute DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS_USES_HOST_PAGE_TABLES, then this call has no effect.

Parameters:

devPtr - pointer to memory to set the advice for

count - size in bytes of the memory range

advice - advice to be applied for the specified memory range

device - device to apply the advice for

ncuMemRangeGetAttribute

public static int ncuMemRangeGetAttribute(long data,
 long dataSize,
 int attribute,
 long devPtr,
 long count)

Unsafe version of: MemRangeGetAttribute

Parameters:

dataSize - the size of data

cuMemRangeGetAttribute

public static int cuMemRangeGetAttribute(ByteBuffer data,
 int attribute,
 long devPtr,
 long count)

Query an attribute of a given memory range.

Query an attribute about the memory range starting at devPtr with a size of count bytes. The memory range must refer to managed memory allocated via MemAllocManaged or declared via __managed__ variables.

The attribute parameter can take the following values:

• MEM_RANGE_ATTRIBUTE_READ_MOSTLY: If this attribute is specified, data will be interpreted as a 32-bit integer, and dataSize must be 4. The result returned will be 1 if all pages in the given memory range have read-duplication enabled, or 0 otherwise.
• MEM_RANGE_ATTRIBUTE_PREFERRED_LOCATION: If this attribute is specified, data will be interpreted as a 32-bit integer, and dataSize must be 4. The result returned will be a GPU device id if all pages in the memory range have that GPU as their preferred location, or it will be CU_DEVICE_CPU if all pages in the memory range have the CPU as their preferred location, or it will be CU_DEVICE_INVALID if either all the pages don't have the same preferred location or some of the pages don't have a preferred location at all. Note that the actual location of the pages in the memory range at the time of the query may be different from the preferred location.
• MEM_RANGE_ATTRIBUTE_ACCESSED_BY: If this attribute is specified, data will be interpreted as an array of 32-bit integers, and dataSize must be a non-zero multiple of 4. The result returned will be a list of device ids that had MEM_ADVISE_SET_ACCESSED_BY set for that entire memory range. If any device does not have that advice set for the entire memory range, that device will not be included. If data is larger than the number of devices that have that advice set for that memory range, CU_DEVICE_INVALID will be returned in all the extra space provided. For ex., if dataSize is 12 (i.e. data has 3 elements) and only device 0 has the advice set, then the result returned will be { 0, CU_DEVICE_INVALID, CU_DEVICE_INVALID }. If data is smaller than the number of devices that have that advice set, then only as many devices will be returned as can fit in the array. There is no guarantee on which specific devices will be returned, however.
• MEM_RANGE_ATTRIBUTE_LAST_PREFETCH_LOCATION: If this attribute is specified, data will be interpreted as a 32-bit integer, and dataSize must be 4. The result returned will be the last location to which all pages in the memory range were prefetched explicitly via MemPrefetchAsync. This will either be a GPU id or CU_DEVICE_CPU depending on whether the last location for prefetch was a GPU or the CPU respectively. If any page in the memory range was never explicitly prefetched or if all pages were not prefetched to the same location, CU_DEVICE_INVALID will be returned. Note that this simply returns the last location that the applicaton requested to prefetch the memory range to. It gives no indication as to whether the prefetch operation to that location has completed or even begun.

Parameters:

data - a pointers to a memory location where the result of each attribute query will be written to

attribute - the attribute to query

devPtr - start of the range to query

count - size of the range to query

ncuMemRangeGetAttributes

public static int ncuMemRangeGetAttributes(long data,
 long dataSizes,
 long attributes,
 long numAttributes,
 long devPtr,
 long count)

Unsafe version of: MemRangeGetAttributes

Parameters:

numAttributes - number of attributes to query

cuMemRangeGetAttributes

public static int cuMemRangeGetAttributes(PointerBuffer data,
 PointerBuffer dataSizes,
 IntBuffer attributes,
 long devPtr,
 long count)

Query attributes of a given memory range.

Query attributes of the memory range starting at devPtr with a size of count bytes. The memory range must refer to managed memory allocated via MemAllocManaged or declared via __managed__ variables. The attributes array will be interpreted to have numAttributes entries. The dataSizes array will also be interpreted to have numAttributes entries. The results of the query will be stored in data.

The list of supported attributes are given below. Please refer to MemRangeGetAttribute for attribute descriptions and restrictions.

• MEM_RANGE_ATTRIBUTE_READ_MOSTLY
• MEM_RANGE_ATTRIBUTE_PREFERRED_LOCATION
• MEM_RANGE_ATTRIBUTE_ACCESSED_BY
• MEM_RANGE_ATTRIBUTE_LAST_PREFETCH_LOCATION

Parameters:

data - a two-dimensional array containing pointers to memory locations where the result of each attribute query will be written to

dataSizes - array containing the sizes of each result

attributes - an array of attributes to query (numAttributes and the number of attributes in this array should match). One of:

MEM_RANGE_ATTRIBUTE_READ_MOSTLY	MEM_RANGE_ATTRIBUTE_PREFERRED_LOCATION
MEM_RANGE_ATTRIBUTE_ACCESSED_BY	MEM_RANGE_ATTRIBUTE_LAST_PREFETCH_LOCATION

devPtr - start of the range to query

count - size of the range to query

ncuPointerSetAttribute

public static int ncuPointerSetAttribute(long value,
 int attribute,
 long ptr)

Unsafe version of: PointerSetAttribute

cuPointerSetAttribute

public static int cuPointerSetAttribute(ByteBuffer value,
 int attribute,
 long ptr)

Set attributes on a previously allocated memory region.

The supported attributes are:

• POINTER_ATTRIBUTE_SYNC_MEMOPS: A boolean attribute that can either be set (1) or unset (0).

  When set, the region of memory that ptr points to is guaranteed to always synchronize memory operations that are synchronous. If there are some previously initiated synchronous memory operations that are pending when this attribute is set, the function does not return until those memory operations are complete. See further documentation in the section titled "API synchronization behavior" to learn more about cases when synchronous memory operations can exhibit asynchronous behavior. value will be considered as a pointer to an unsigned integer to which this attribute is to be set.

Parameters:

value - pointer to memory containing the value to be set

attribute - pointer attribute to set

ptr - pointer to a memory region allocated using CUDA memory allocation APIs

ncuPointerGetAttributes

public static int ncuPointerGetAttributes(int numAttributes,
 long attributes,
 long data,
 long ptr)

Unsafe version of: PointerGetAttributes

Parameters:

numAttributes - number of attributes to query

cuPointerGetAttributes

public static int cuPointerGetAttributes(IntBuffer attributes,
 PointerBuffer data,
 long ptr)

Returns information about a pointer.

Unlike PointerGetAttribute, this function will not return an error when the ptr encountered is not a valid CUDA pointer. Instead, the attributes are assigned default NULL values and CUDA_SUCCESS is returned.

If ptr was not allocated by, mapped by, or registered with a CUcontext which uses UVA (Unified Virtual Addressing), CUDA_ERROR_INVALID_CONTEXT is returned.

Parameters:

attributes - an array of attributes to query (numAttributes and the number of attributes in this array should match). One of:

POINTER_ATTRIBUTE_CONTEXT	POINTER_ATTRIBUTE_MEMORY_TYPE
POINTER_ATTRIBUTE_DEVICE_POINTER	POINTER_ATTRIBUTE_HOST_POINTER
POINTER_ATTRIBUTE_P2P_TOKENS	POINTER_ATTRIBUTE_SYNC_MEMOPS
POINTER_ATTRIBUTE_BUFFER_ID	POINTER_ATTRIBUTE_IS_MANAGED
POINTER_ATTRIBUTE_DEVICE_ORDINAL	POINTER_ATTRIBUTE_IS_LEGACY_CUDA_IPC_CAPABLE
POINTER_ATTRIBUTE_RANGE_START_ADDR	POINTER_ATTRIBUTE_RANGE_SIZE
POINTER_ATTRIBUTE_MAPPED	POINTER_ATTRIBUTE_ALLOWED_HANDLE_TYPES
POINTER_ATTRIBUTE_IS_GPU_DIRECT_RDMA_CAPABLE	POINTER_ATTRIBUTE_ACCESS_FLAGS
POINTER_ATTRIBUTE_MEMPOOL_HANDLE	POINTER_ATTRIBUTE_ACCESS_FLAG_NONE
POINTER_ATTRIBUTE_ACCESS_FLAG_READ	POINTER_ATTRIBUTE_ACCESS_FLAG_READWRITE

data - a two-dimensional array containing pointers to memory locations where the result of each attribute query will be written to

ptr - pointer to query

ncuStreamCreate

public static int ncuStreamCreate(long phStream,
 int Flags)

Unsafe version of: StreamCreate

cuStreamCreate

public static int cuStreamCreate(PointerBuffer phStream,
 int Flags)

Create a stream.

Creates a stream and returns a handle in phStream. The Flags argument determines behaviors of the stream.

Valid values for Flags are:

• STREAM_DEFAULT: Default stream creation flag.
• STREAM_NON_BLOCKING: Specifies that work running in the created stream may run concurrently with work in stream 0 (the NULL stream), and that the created stream should perform no implicit synchronization with stream 0.

Parameters:

phStream - returned newly created stream

Flags - parameters for stream creation

ncuStreamCreateWithPriority

public static int ncuStreamCreateWithPriority(long phStream,
 int flags,
 int priority)

Unsafe version of: StreamCreateWithPriority

cuStreamCreateWithPriority

public static int cuStreamCreateWithPriority(PointerBuffer phStream,
 int flags,
 int priority)

Create a stream with the given priority.

Creates a stream with the specified priority and returns a handle in phStream. This API alters the scheduler priority of work in the stream. Work in a higher priority stream may preempt work already executing in a low priority stream.

priority follows a convention where lower numbers represent higher priorities. 0 represents default priority. The range of meaningful numerical priorities can be queried using CtxGetStreamPriorityRange. If the specified priority is outside the numerical range returned by CtxGetStreamPriorityRange, it will automatically be clamped to the lowest or the highest number in the range.

Note

Stream priorities are supported only on GPUs with compute capability 3.5 or higher.

Note

In the current implementation, only compute kernels launched in priority streams are affected by the stream's priority. Stream priorities have no effect on host-to-device and device-to-host memory operations.

Parameters:

phStream - returned newly created stream

flags - flags for stream creation. See StreamCreate for a list of valid flags

priority - stream priority. Lower numbers represent higher priorities. See CtxGetStreamPriorityRange for more information about meaningful stream priorities that can be passed.

ncuStreamGetPriority

public static int ncuStreamGetPriority(long hStream,
 long priority)

Unsafe version of: StreamGetPriority

cuStreamGetPriority

public static int cuStreamGetPriority(long hStream,
 IntBuffer priority)

Query the priority of a given stream.

Query the priority of a stream created using StreamCreate or StreamCreateWithPriority and return the priority in priority. Note that if the stream was created with a priority outside the numerical range returned by CtxGetStreamPriorityRange, this function returns the clamped priority. See StreamCreateWithPriority for details about priority clamping.

Parameters:

hStream - handle to the stream to be queried

priority - pointer to a signed integer in which the stream's priority is returned

ncuStreamGetFlags

public static int ncuStreamGetFlags(long hStream,
 long flags)

Unsafe version of: StreamGetFlags

cuStreamGetFlags

public static int cuStreamGetFlags(long hStream,
 IntBuffer flags)

Query the flags of a given stream.

Query the flags of a stream created using StreamCreate or StreamCreateWithPriority and return the flags in flags.

Parameters:

hStream - handle to the stream to be queried

flags - pointer to an unsigned integer in which the stream's flags are returned The value returned in flags is a logical 'OR' of all flags that were used while creating this stream. See StreamCreate for the list of valid flags.

ncuStreamGetCtx

public static int ncuStreamGetCtx(long hStream,
 long pctx)

Unsafe version of: StreamGetCtx

cuStreamGetCtx

public static int cuStreamGetCtx(long hStream,
 PointerBuffer pctx)

Query the context associated with a stream.

Returns the CUDA context that the stream is associated with.

The stream handle hStream can refer to any of the following:

• a stream created via any of the CUDA driver APIs such as StreamCreate and StreamCreateWithPriority, or their runtime API equivalents such as cudaStreamCreate(), cudaStreamCreateWithFlags() and cudaStreamCreateWithPriority(). The returned context is the context that was active in the calling thread when the stream was created. Passing an invalid handle will result in undefined behavior.
• any of the special streams such as the NULL stream, STREAM_LEGACY and STREAM_PER_THREAD. The runtime API equivalents of these are also accepted, which are NULL, cudaStreamLegacy() and cudaStreamPerThread() respectively. Specifying any of the special handles will return the context current to the calling thread. If no context is current to the calling thread, CUDA_ERROR_INVALID_CONTEXT is returned.

Parameters:

hStream - handle to the stream to be queried

pctx - returned context associated with the stream

cuStreamWaitEvent

public static int cuStreamWaitEvent(long hStream,
 long hEvent,
 int Flags)

Make a compute stream wait on an event.

Makes all future work submitted to hStream wait for all work captured in hEvent. See EventRecord for details on what is captured by an event. The synchronization will be performed efficiently on the device when applicable. hEvent may be from a different context or device than hStream.

Parameters:

hStream - stream to wait

hEvent - event to wait on (may not be NULL). One of:

EVENT_WAIT_DEFAULT

EVENT_WAIT_EXTERNAL

Flags - see CUevent_capture_flags

ncuStreamAddCallback

public static int ncuStreamAddCallback(long hStream,
 long callback,
 long userData,
 int flags)

Unsafe version of: StreamAddCallback

cuStreamAddCallback

public static int cuStreamAddCallback(long hStream,
 CUstreamCallbackI callback,
 long userData,
 int flags)

Add a callback to a compute stream.

Note

This function is slated for eventual deprecation and removal. If you do not require the callback to execute in case of a device error, consider using LaunchHostFunc. Additionally, this function is not supported with StreamBeginCapture and StreamEndCapture, unlike LaunchHostFunc.

Adds a callback to be called on the host after all currently enqueued items in the stream have completed. For each cuStreamAddCallback call, the callback will be executed exactly once. The callback will block later work in the stream until it is finished.

The callback may be passed CUDA_SUCCESS or an error code. In the event of a device error, all subsequently executed callbacks will receive an appropriate CUresult.

Callbacks must not make any CUDA API calls. Attempting to use a CUDA API will result in CUDA_ERROR_NOT_PERMITTED. Callbacks must not perform any synchronization that may depend on outstanding device work or other callbacks that are not mandated to run earlier. Callbacks without a mandated order (in independent streams) execute in undefined order and may be serialized.

For the purposes of Unified Memory, callback execution makes a number of guarantees:

• The callback stream is considered idle for the duration of the callback. Thus, for example, a callback may always use memory attached to the callback stream.
• The start of execution of a callback has the same effect as synchronizing an event recorded in the same stream immediately prior to the callback. It thus synchronizes streams which have been "joined" prior to the callback.
• Adding device work to any stream does not have the effect of making the stream active until all preceding host functions and stream callbacks have executed. Thus, for example, a callback might use global attached memory even if work has been added to another stream, if the work has been ordered behind the callback with an event.
• Completion of a callback does not cause a stream to become active except as described above. The callback stream will remain idle if no device work follows the callback, and will remain idle across consecutive callbacks without device work in between. Thus, for example, stream synchronization can be done by signaling from a callback at the end of the stream.

Parameters:

hStream - stream to add callback to

callback - the function to call once preceding stream operations are complete

userData - user specified data to be passed to the callback function

flags - reserved for future use, must be 0

cuStreamBeginCapture

public static int cuStreamBeginCapture(long hStream)

Begins graph capture on a stream.

Begin graph capture on hStream. When a stream is in capture mode, all operations pushed into the stream will not be executed, but will instead be captured into a graph, which will be returned via StreamEndCapture. Capture may not be initiated if stream is STREAM_LEGACY. Capture must be ended on the same stream in which it was initiated, and it may only be initiated if the stream is not already in capture mode. The capture mode may be queried via StreamIsCapturing. A unique id representing the capture sequence may be queried via StreamGetCaptureInfo.

Note

Kernels captured using this API must not use texture and surface references. Reading or writing through any texture or surface reference is undefined behavior. This restriction does not apply to texture and surface objects.

Parameters:

hStream - stream in which to initiate capture

cuStreamBeginCapture_v2

public static int cuStreamBeginCapture_v2(long hStream,
 int mode)

Begins graph capture on a stream.

Begin graph capture on hStream. When a stream is in capture mode, all operations pushed into the stream will not be executed, but will instead be captured into a graph, which will be returned via StreamEndCapture. Capture may not be initiated if stream is STREAM_LEGACY. Capture must be ended on the same stream in which it was initiated, and it may only be initiated if the stream is not already in capture mode. The capture mode may be queried via StreamIsCapturing. A unique id representing the capture sequence may be queried via StreamGetCaptureInfo.

If mode is not STREAM_CAPTURE_MODE_RELAXED, StreamEndCapture must be called on this stream from the same thread.

Note

Kernels captured using this API must not use texture and surface references. Reading or writing through any texture or surface reference is undefined behavior. This restriction does not apply to texture and surface objects.

Parameters:

hStream - stream in which to initiate capture

mode - controls the interaction of this capture sequence with other API calls that are potentially unsafe. For more details see ThreadExchangeStreamCaptureMode.

ncuThreadExchangeStreamCaptureMode

public static int ncuThreadExchangeStreamCaptureMode(long mode)

Unsafe version of: ThreadExchangeStreamCaptureMode

cuThreadExchangeStreamCaptureMode

public static int cuThreadExchangeStreamCaptureMode(IntBuffer mode)

Swaps the stream capture interaction mode for a thread.

Sets the calling thread's stream capture interaction mode to the value contained in *mode, and overwrites *mode with the previous mode for the thread. To facilitate deterministic behavior across function or module boundaries, callers are encouraged to use this API in a push-pop fashion:

 CUstreamCaptureMode mode = desiredMode
 cuThreadExchangeStreamCaptureMode(&mode);
 ...
 cuThreadExchangeStreamCaptureMode(&mode); // restore previous mode

During stream capture (see StreamBeginCapture), some actions, such as a call to cudaMalloc, may be unsafe. In the case of cudaMalloc, the operation is not enqueued asynchronously to a stream, and is not observed by stream capture. Therefore, if the sequence of operations captured via StreamBeginCapture depended on the allocation being replayed whenever the graph is launched, the captured graph would be invalid.

Therefore, stream capture places restrictions on API calls that can be made within or concurrently to a StreamBeginCapture-StreamEndCapture sequence. This behavior can be controlled via this API and flags to cuStreamBeginCapture.

A thread's mode is one of the following:

• STREAM_CAPTURE_MODE_GLOBAL: This is the default mode.

  If the local thread has an ongoing capture sequence that was not initiated with STREAM_CAPTURE_MODE_RELAXED at StreamBeginCapture, or if any other thread has a concurrent capture sequence initiated with STREAM_CAPTURE_MODE_GLOBAL, this thread is prohibited from potentially unsafe API calls.

• STREAM_CAPTURE_MODE_THREAD_LOCAL: If the local thread has an ongoing capture sequence not initiated with CU_STREAM_CAPTURE_MODE_RELAXED, it is prohibited from potentially unsafe API calls. Concurrent capture sequences in other threads are ignored.
• STREAM_CAPTURE_MODE_RELAXED: The local thread is not prohibited from potentially unsafe API calls. Note that the thread is still prohibited from API calls which necessarily conflict with stream capture, for example, attempting EventQuery on an event that was last recorded inside a capture sequence.

Parameters:

mode - pointer to mode value to swap with the current mode

ncuStreamEndCapture

public static int ncuStreamEndCapture(long hStream,
 long phGraph)

Unsafe version of: StreamEndCapture

cuStreamEndCapture

public static int cuStreamEndCapture(long hStream,
 PointerBuffer phGraph)

Ends capture on a stream, returning the captured graph.

End capture on hStream, returning the captured graph via phGraph. Capture must have been initiated on hStream via a call to StreamBeginCapture. If capture was invalidated, due to a violation of the rules of stream capture, then a NULL graph will be returned.

If the mode argument to StreamBeginCapture was not STREAM_CAPTURE_MODE_RELAXED, this call must be from the same thread as StreamBeginCapture.

Parameters:

hStream - stream to query

phGraph - the captured graph

ncuStreamIsCapturing

public static int ncuStreamIsCapturing(long hStream,
 long captureStatus)

Unsafe version of: StreamIsCapturing

cuStreamIsCapturing

public static int cuStreamIsCapturing(long hStream,
 IntBuffer captureStatus)

Returns a stream's capture status.

Return the capture status of hStream via captureStatus. After a successful call, *captureStatus will contain one of the following:

• STREAM_CAPTURE_STATUS_NONE: The stream is not capturing.
• STREAM_CAPTURE_STATUS_ACTIVE: The stream is capturing.
• STREAM_CAPTURE_STATUS_INVALIDATED: The stream was capturing but an error has invalidated the capture sequence. The capture sequence must be terminated with StreamEndCapture on the stream where it was initiated in order to continue using hStream.

Note that, if this is called on STREAM_LEGACY (the "null stream") while a blocking stream in the same context is capturing, it will return CUDA_ERROR_STREAM_CAPTURE_IMPLICIT and *captureStatus is unspecified after the call. The blocking stream capture is not invalidated.

When a blocking stream is capturing, the legacy stream is in an unusable state until the blocking stream capture is terminated. The legacy stream is not supported for stream capture, but attempted use would have an implicit dependency on the capturing stream(s).

Parameters:

hStream - stream to query

captureStatus - returns the stream's capture status

ncuStreamGetCaptureInfo

public static int ncuStreamGetCaptureInfo(long hStream,
 long captureStatus,
 long id)

Unsafe version of: StreamGetCaptureInfo

cuStreamGetCaptureInfo

public static int cuStreamGetCaptureInfo(long hStream,
 IntBuffer captureStatus,
 LongBuffer id)

Query capture status of a stream.

Query the capture status of a stream and and get an id for the capture sequence, which is unique over the lifetime of the process.

If called on STREAM_LEGACY (the "null stream") while a stream not created with STREAM_NON_BLOCKING is capturing, returns CUDA_ERROR_STREAM_CAPTURE_IMPLICIT.

A valid id is returned only if both of the following are true:

• the call returns SUCCESS
• captureStatus is set to STREAM_CAPTURE_STATUS_ACTIVE

ncuStreamGetCaptureInfo_v2

public static int ncuStreamGetCaptureInfo_v2(long hStream,
 long captureStatus_out,
 long id_out,
 long graph_out,
 long dependencies_out,
 long numDependencies_out)

Unsafe version of: StreamGetCaptureInfo_v2

cuStreamGetCaptureInfo_v2

public static int cuStreamGetCaptureInfo_v2(long hStream,
 IntBuffer captureStatus_out,
 @Nullable
 LongBuffer id_out,
 @Nullable
 PointerBuffer graph_out,
 @Nullable
 PointerBuffer dependencies_out,
 @Nullable
 PointerBuffer numDependencies_out)

Query a stream's capture state (11.3+).

Query stream state related to stream capture.

If called on STREAM_LEGACY (the "null stream") while a stream not created with STREAM_NON_BLOCKING is capturing, returns CUDA_ERROR_STREAM_CAPTURE_IMPLICIT.

Valid data (other than capture status) is returned only if both of the following are true:

• the call returns CUDA_SUCCESS
• the returned capture status is STREAM_CAPTURE_STATUS_ACTIVE

This version of cuStreamGetCaptureInfo is introduced in CUDA 11.3 and will supplant the previous version in 12.0. Developers requiring compatibility across minor versions to CUDA 11.0 (driver version 445) should use StreamGetCaptureInfo or include a fallback path.

Parameters:

hStream - the stream to query

captureStatus_out - location to return the capture status of the stream; required

id_out - optional location to return an id for the capture sequence, which is unique over the lifetime of the process

graph_out - optional location to return the graph being captured into.

All operations other than destroy and node removal are permitted on the graph while the capture sequence is in progress. This API does not transfer ownership of the graph, which is transferred or destroyed at StreamEndCapture. Note that the graph handle may be invalidated before end of capture for certain errors. Nodes that are or become unreachable from the original stream at StreamEndCapture due to direct actions on the graph do not trigger CUDA_ERROR_STREAM_CAPTURE_UNJOINED.

dependencies_out - optional location to store a pointer to an array of nodes.

The next node to be captured in the stream will depend on this set of nodes, absent operations such as event wait which modify this set. The array pointer is valid until the next API call which operates on the stream or until end of capture. The node handles may be copied out and are valid until they or the graph is destroyed. The driver-owned array may also be passed directly to APIs that operate on the graph (not the stream) without copying.

numDependencies_out - optional location to store the size of the array returned in dependencies_out

ncuStreamUpdateCaptureDependencies

public static int ncuStreamUpdateCaptureDependencies(long hStream,
 long dependencies,
 long numDependencies,
 int flags)

Unsafe version of: StreamUpdateCaptureDependencies

cuStreamUpdateCaptureDependencies

public static int cuStreamUpdateCaptureDependencies(long hStream,
 PointerBuffer dependencies,
 int flags)

Update the set of dependencies in a capturing stream (11.3+).

Modifies the dependency set of a capturing stream. The dependency set is the set of nodes that the next captured node in the stream will depend on.

Valid flags are STREAM_ADD_CAPTURE_DEPENDENCIES and STREAM_SET_CAPTURE_DEPENDENCIES. These control whether the set passed to the API is added to the existing set or replaces it. A flags value of 0 defaults to STREAM_ADD_CAPTURE_DEPENDENCIES.

Nodes that are removed from the dependency set via this API do not result in CUDA_ERROR_STREAM_CAPTURE_UNJOINED if they are unreachable from the stream at StreamEndCapture.

Returns CUDA_ERROR_ILLEGAL_STATE if the stream is not capturing.

This API is new in CUDA 11.3. Developers requiring compatibility across minor versions to CUDA 11.0 should not use this API or provide a fallback.

cuStreamAttachMemAsync

public static int cuStreamAttachMemAsync(long hStream,
 long dptr,
 long length,
 int flags)

Attach memory to a stream asynchronously.

Enqueues an operation in hStream to specify stream association of length bytes of memory starting from dptr. This function is a stream-ordered operation, meaning that it is dependent on, and will only take effect when, previous work in stream has completed. Any previous association is automatically replaced.

dptr must point to one of the following types of memories:

• managed memory declared using the __managed__ keyword or allocated with MemAllocManaged.
• a valid host-accessible region of system-allocated pageable memory. This type of memory may only be specified if the device associated with the stream reports a non-zero value for the device attribute DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS.

For managed allocations, length must be either zero or the entire allocation's size. Both indicate that the entire allocation's stream association is being changed. Currently, it is not possible to change stream association for a portion of a managed allocation.

For pageable host allocations, length must be non-zero.

The stream association is specified using flags which must be one of CUmemAttach_flags. If the MEM_ATTACH_GLOBAL flag is specified, the memory can be accessed by any stream on any device. If the MEM_ATTACH_HOST flag is specified, the program makes a guarantee that it won't access the memory on the device from any stream on a device that has a zero value for the device attribute DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS. If the MEM_ATTACH_SINGLE flag is specified and hStream is associated with a device that has a zero value for the device attribute DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS, the program makes a guarantee that it will only access the memory on the device from hStream. It is illegal to attach singly to the NULL stream, because the NULL stream is a virtual global stream and not a specific stream. An error will be returned in this case.

When memory is associated with a single stream, the Unified Memory system will allow CPU access to this memory region so long as all operations in hStream have completed, regardless of whether other streams are active. In effect, this constrains exclusive ownership of the managed memory region by an active GPU to per-stream activity instead of whole-GPU activity.

Accessing memory on the device from streams that are not associated with it will produce undefined results. No error checking is performed by the Unified Memory system to ensure that kernels launched into other streams do not access this region.

It is a program's responsibility to order calls to StreamAttachMemAsync via events, synchronization or other means to ensure legal access to memory at all times. Data visibility and coherency will be changed appropriately for all kernels which follow a stream-association change.

If hStream is destroyed while data is associated with it, the association is removed and the association reverts to the default visibility of the allocation as specified at MemAllocManaged. For __managed__ variables, the default association is always MEM_ATTACH_GLOBAL. Note that destroying a stream is an asynchronous operation, and as a result, the change to default association won't happen until all work in the stream has completed.

Parameters:

hStream - stream in which to enqueue the attach operation

dptr - pointer to memory (must be a pointer to managed memory or to a valid host-accessible region of system-allocated pageable memory)

length - length of memory

flags - must be one of CUmemAttach_flags

cuStreamQuery

public static int cuStreamQuery(long hStream)

Determine status of a compute stream.

Returns CUDA_SUCCESS if all operations in the stream specified by hStream have completed, or CUDA_ERROR_NOT_READY if not.

For the purposes of Unified Memory, a return value of CUDA_SUCCESS is equivalent to having called StreamSynchronize.

Parameters:

hStream - stream to query status of

cuStreamSynchronize

public static int cuStreamSynchronize(long hStream)

Wait until a stream's tasks are completed.

Waits until the device has completed all operations in the stream specified by hStream. If the context was created with the CTX_SCHED_BLOCKING_SYNC flag, the CPU thread will block until the stream is finished with all of its tasks.

Parameters:

hStream - stream to wait for

cuStreamDestroy

public static int cuStreamDestroy(long hStream)

Destroys a stream.

Destroys the stream specified by hStream.

In case the device is still doing work in the stream hStream when StreamDestroy is called, the function will return immediately and the resources associated with hStream will be released automatically once the device has completed all work in hStream.

Parameters:

hStream - stream to destroy

cuStreamCopyAttributes

public static int cuStreamCopyAttributes(long dst,
 long src)

Copies attributes from source stream to destination stream.

Copies attributes from source stream src to destination stream dst. Both streams must have the same context.

Parameters:

dst - destination stream

src - source stream For list of attributes see CUstreamAttrID

ncuStreamGetAttribute

public static int ncuStreamGetAttribute(long hStream,
 int attr,
 long value_out)

Unsafe version of: StreamGetAttribute

cuStreamGetAttribute

public static int cuStreamGetAttribute(long hStream,
 int attr,
 CUstreamAttrValue value_out)

Queries stream attribute.

Queries attribute attr from hStream and stores it in corresponding member of value_out.

ncuStreamSetAttribute

public static int ncuStreamSetAttribute(long hStream,
 int attr,
 long value)

Unsafe version of: StreamSetAttribute

cuStreamSetAttribute

public static int cuStreamSetAttribute(long hStream,
 int attr,
 CUstreamAttrValue value)

Sets stream attribute.

Sets attribute attr on hStream from corresponding attribute of value. The updated attribute will be applied to subsequent work submitted to the stream. It will not affect previously submitted work.

ncuEventCreate

public static int ncuEventCreate(long phEvent,
 int Flags)

Unsafe version of: EventCreate

cuEventCreate

public static int cuEventCreate(PointerBuffer phEvent,
 int Flags)

Creates an event.

Creates an event *phEvent for the current context with the flags specified via Flags. Valid flags include:

• EVENT_DEFAULT: Default event creation flag.
• EVENT_BLOCKING_SYNC: Specifies that the created event should use blocking synchronization. A CPU thread that uses EventSynchronize to wait on an event created with this flag will block until the event has actually been recorded.
• EVENT_DISABLE_TIMING: Specifies that the created event does not need to record timing data. Events created with this flag specified and the EVENT_BLOCKING_SYNC flag not specified will provide the best performance when used with StreamWaitEvent and EventQuery.
• EVENT_INTERPROCESS: Specifies that the created event may be used as an interprocess event by IpcGetEventHandle. EVENT_INTERPROCESS must be specified along with EVENT_DISABLE_TIMING.

Parameters:

phEvent - returns newly created event

Flags - event creation flags

cuEventRecord

public static int cuEventRecord(long hEvent,
 long hStream)

Records an event.

Captures in hEvent the contents of hStream at the time of this call. hEvent and hStream must be from the same context. Calls such as EventQuery or StreamWaitEvent will then examine or wait for completion of the work that was captured. Uses of hStream after this call do not modify hEvent. See note on default stream behavior for what is captured in the default case.

EventRecord can be called multiple times on the same event and will overwrite the previously captured state. Other APIs such as StreamWaitEvent use the most recently captured state at the time of the API call, and are not affected by later calls to EventRecord. Before the first call to EventRecord, an event represents an empty set of work, so for example EventQuery would return CUDA_SUCCESS.

Parameters:

hEvent - event to record

hStream - stream to record event for

cuEventRecordWithFlags

public static int cuEventRecordWithFlags(long hEvent,
 long hStream,
 int flags)

Records an event.

Captures in hEvent the contents of hStream at the time of this call. hEvent and hStream must be from the same context. Calls such as EventQuery or StreamWaitEvent will then examine or wait for completion of the work that was captured. Uses of hStream after this call do not modify hEvent. See note on default stream behavior for what is captured in the default case.

EventRecordWithFlags can be called multiple times on the same event and will overwrite the previously captured state. Other APIs such as StreamWaitEvent use the most recently captured state at the time of the API call, and are not affected by later calls to EventRecordWithFlags. Before the first call to EventRecordWithFlags, an event represents an empty set of work, so for example EventQuery would return CUDA_SUCCESS.

flags include:

• EVENT_RECORD_DEFAULT: Default event creation flag.
• EVENT_RECORD_EXTERNAL: Event is captured in the graph as an external event node when performing stream capture. This flag is invalid outside of stream capture.

Parameters:

hEvent - event to record

hStream - stream to record event for

flags - see CUevent_capture_flags

cuEventQuery

public static int cuEventQuery(long hEvent)

Queries an event's status.

Queries the status of all work currently captured by hEvent. See EventRecord for details on what is captured by an event.

Returns CUDA_SUCCESS if all captured work has been completed, or CUDA_ERROR_NOT_READY if any captured work is incomplete.

For the purposes of Unified Memory, a return value of CUDA_SUCCESS is equivalent to having called EventSynchronize.

Parameters:

hEvent - event to query

cuEventSynchronize

public static int cuEventSynchronize(long hEvent)

Waits for an event to complete.

Waits until the completion of all work currently captured in hEvent. See EventRecord for details on what is captured by an event.

Waiting for an event that was created with the EVENT_BLOCKING_SYNC flag will cause the calling CPU thread to block until the event has been completed by the device. If the EVENT_BLOCKING_SYNC flag has not been set, then the CPU thread will busy-wait until the event has been completed by the device.

Parameters:

hEvent - event to wait for

cuEventDestroy

public static int cuEventDestroy(long hEvent)

Destroys an event.

Destroys the event specified by hEvent.

An event may be destroyed before it is complete (i.e., while EventQuery would return CUDA_ERROR_NOT_READY). In this case, the call does not block on completion of the event, and any associated resources will automatically be released asynchronously at completion.

Parameters:

hEvent - event to destroy

ncuEventElapsedTime

public static int ncuEventElapsedTime(long pMilliseconds,
 long hStart,
 long hEnd)

Unsafe version of: EventElapsedTime

cuEventElapsedTime

public static int cuEventElapsedTime(FloatBuffer pMilliseconds,
 long hStart,
 long hEnd)

Computes the elapsed time between two events.

Computes the elapsed time between two events (in milliseconds with a resolution of around 0.5 microseconds).

If either event was last recorded in a non-NULL stream, the resulting time may be greater than expected (even if both used the same stream handle). This happens because the EventRecord operation takes place asynchronously and there is no guarantee that the measured latency is actually just between the two events. Any number of other different stream operations could execute in between the two measured events, thus altering the timing in a significant way.

If EventRecord has not been called on either event then CUDA_ERROR_INVALID_HANDLE is returned. If EventRecord has been called on both events but one or both of them has not yet been completed (that is, EventQuery would return CUDA_ERROR_NOT_READY on at least one of the events), CUDA_ERROR_NOT_READY is returned. If either event was created with the EVENT_DISABLE_TIMING flag, then this function will return CUDA_ERROR_INVALID_HANDLE.

Parameters:

pMilliseconds - time between hStart and hEnd in ms

hStart - starting event

hEnd - ending event

ncuImportExternalMemory

public static int ncuImportExternalMemory(long extMem_out,
 long memHandleDesc)

Unsafe version of: ImportExternalMemory

cuImportExternalMemory

public static int cuImportExternalMemory(PointerBuffer extMem_out,
 CUDA_EXTERNAL_MEMORY_HANDLE_DESC memHandleDesc)

Imports an external memory object.

Imports an externally allocated memory object and returns a handle to that in extMem_out.

The properties of the handle being imported must be described in memHandleDesc.

If ::type is EXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_FD, then ::handle::fd must be a valid file descriptor referencing a memory object. Ownership of the file descriptor is transferred to the CUDA driver when the handle is imported successfully. Performing any operations on the file descriptor after it is imported results in undefined behavior.

If ::type is EXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_WIN32, then exactly one of ::handle::win32::handle and ::handle::win32::name must not be NULL. If ::handle::win32::handle is not NULL, then it must represent a valid shared NT handle that references a memory object. Ownership of this handle is not transferred to CUDA after the import operation, so the application must release the handle using the appropriate system call. If ::handle::win32::name is not NULL, then it must point to a NULL-terminated array of UTF-16 characters that refers to a memory object.

If ::type is EXTERNAL_MEMORY_HANDLE_TYPE_OPAQUE_WIN32_KMT, then ::handle::win32::handle must be non-NULL and ::handle::win32::name must be NULL. The handle specified must be a globally shared KMT handle. This handle does not hold a reference to the underlying object, and thus will be invalid when all references to the memory object are destroyed.

If ::type is EXTERNAL_MEMORY_HANDLE_TYPE_D3D12_HEAP, then exactly one of ::handle::win32::handle and ::handle::win32::name must not be NULL. If ::handle::win32::handle is not NULL, then it must represent a valid shared NT handle that is returned by ID3D12Device::CreateSharedHandle when referring to a ID3D12Heap object. This handle holds a reference to the underlying object. If ::handle::win32::name is not NULL, then it must point to a NULL-terminated array of UTF-16 characters that refers to a ID3D12Heap object.

If ::type is EXTERNAL_MEMORY_HANDLE_TYPE_D3D12_RESOURCE, then exactly one of ::handle::win32::handle and ::handle::win32::name must not be NULL. If ::handle::win32::handle is not NULL, then it must represent a valid shared NT handle that is returned by ID3D12Device::CreateSharedHandle when referring to a ID3D12Resource object. This handle holds a reference to the underlying object. If ::handle::win32::name is not NULL, then it must point to a NULL-terminated array of UTF-16 characters that refers to a ID3D12Resource object.

If ::type is EXTERNAL_MEMORY_HANDLE_TYPE_D3D11_RESOURCE, then ::handle::win32::handle must represent a valid shared NT handle that is\ returned by IDXGIResource1::CreateSharedHandle when referring to a ID3D11Resource object. If ::handle::win32::name is not NULL, then it must point to a NULL-terminated array of UTF-16 characters that refers to a ID3D11Resource object.

If ::type is EXTERNAL_MEMORY_HANDLE_TYPE_D3D11_RESOURCE_KMT, then ::handle::win32::handle must represent a valid shared KMT handle that is returned by IDXGIResource::GetSharedHandle when referring to a ID3D11Resource object and ::handle::win32::name must be NULL.

If ::type is EXTERNAL_MEMORY_HANDLE_TYPE_NVSCIBUF, then ::handle::nvSciBufObject must be non-NULL and reference a valid NvSciBuf object. If the NvSciBuf object imported into CUDA is also mapped by other drivers, then the application must use WaitExternalSemaphoresAsync or SignalExternalSemaphoresAsync as appropriate barriers to maintain coherence between CUDA and the other drivers. See CUDA_EXTERNAL_SEMAPHORE_SIGNAL_SKIP_NVSCIBUF_MEMSYNC and CUDA_EXTERNAL_SEMAPHORE_WAIT_SKIP_NVSCIBUF_MEMSYNC for memory synchronization.

The size of the memory object must be specified in ::size.

Specifying the flag CUDA_EXTERNAL_MEMORY_DEDICATED in ::flags indicates that the resource is a dedicated resource. The definition of what a dedicated resource is outside the scope of this extension. This flag must be set if ::type is one of the following:

• EXTERNAL_MEMORY_HANDLE_TYPE_D3D12_RESOURCE
• EXTERNAL_MEMORY_HANDLE_TYPE_D3D11_RESOURCE
• EXTERNAL_MEMORY_HANDLE_TYPE_D3D11_RESOURCE_KMT

Note

If the Vulkan memory imported into CUDA is mapped on the CPU then the application must use vkInvalidateMappedMemoryRanges/vkFlushMappedMemoryRanges as well as appropriate Vulkan pipeline barriers to maintain coherence between CPU and GPU. For more information on these APIs, please refer to "Synchronization and Cache Control" chapter from Vulkan specification.

Parameters:

extMem_out - returned handle to an external memory object

memHandleDesc - memory import handle descriptor

ncuExternalMemoryGetMappedBuffer

public static int ncuExternalMemoryGetMappedBuffer(long devPtr,
 long extMem,
 long bufferDesc)

Unsafe version of: ExternalMemoryGetMappedBuffer

cuExternalMemoryGetMappedBuffer

public static int cuExternalMemoryGetMappedBuffer(PointerBuffer devPtr,
 long extMem,
 CUDA_EXTERNAL_MEMORY_BUFFER_DESC bufferDesc)

Maps a buffer onto an imported memory object.

Maps a buffer onto an imported memory object and returns a device pointer in devPtr.

The properties of the buffer being mapped must be described in bufferDesc.

The offset and size have to be suitably aligned to match the requirements of the external API. Mapping two buffers whose ranges overlap may or may not result in the same virtual address being returned for the overlapped portion. In such cases, the application must ensure that all accesses to that region from the GPU are volatile. Otherwise writes made via one address are not guaranteed to be visible via the other address, even if they're issued by the same thread. It is recommended that applications map the combined range instead of mapping separate buffers and then apply the appropriate offsets to the returned pointer to derive the individual buffers.

The returned pointer devPtr must be freed using MemFree.

Parameters:

devPtr - returned device pointer to buffer

extMem - handle to external memory object

bufferDesc - buffer descriptor

ncuExternalMemoryGetMappedMipmappedArray

public static int ncuExternalMemoryGetMappedMipmappedArray(long mipmap,
 long extMem,
 long mipmapDesc)

Unsafe version of: ExternalMemoryGetMappedMipmappedArray

cuExternalMemoryGetMappedMipmappedArray

public static int cuExternalMemoryGetMappedMipmappedArray(PointerBuffer mipmap,
 long extMem,
 CUDA_EXTERNAL_MEMORY_MIPMAPPED_ARRAY_DESC mipmapDesc)

Maps a CUDA mipmapped array onto an external memory object.

Maps a CUDA mipmapped array onto an external object and returns a handle to it in mipmap.

The properties of the CUDA mipmapped array being mapped must be described in mipmapDesc.

::offset is the offset in the memory object where the base level of the mipmap chain is. ::arrayDesc describes the format, dimensions and type of the base level of the mipmap chain. For further details on these parameters, please refer to the documentation for MipmappedArrayCreate. Note that if the mipmapped array is bound as a color target in the graphics API, then the flag CUDA_ARRAY3D_COLOR_ATTACHMENT must be specified in ::arrayDesc::Flags. ::numLevels specifies the total number of levels in the mipmap chain.

If extMem was imported from a handle of type EXTERNAL_MEMORY_HANDLE_TYPE_NVSCIBUF, then ::numLevels must be equal to 1.

The returned CUDA mipmapped array must be freed using MipmappedArrayDestroy.

Parameters:

mipmap - returned CUDA mipmapped array

extMem - handle to external memory object

mipmapDesc - CUDA array descriptor

cuDestroyExternalMemory

public static int cuDestroyExternalMemory(long extMem)

Destroys an external memory object.

Destroys the specified external memory object. Any existing buffers and CUDA mipmapped arrays mapped onto this object must no longer be used and must be explicitly freed using MemFree and MipmappedArrayDestroy respectively.

Parameters:

extMem - external memory object to be destroyed

ncuImportExternalSemaphore

public static int ncuImportExternalSemaphore(long extSem_out,
 long semHandleDesc)

Unsafe version of: ImportExternalSemaphore

cuImportExternalSemaphore

public static int cuImportExternalSemaphore(PointerBuffer extSem_out,
 CUDA_EXTERNAL_SEMAPHORE_HANDLE_DESC semHandleDesc)

Imports an external semaphore.

Imports an externally allocated synchronization object and returns a handle to that in extSem_out.

The properties of the handle being imported must be described in semHandleDesc.

If ::type is EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_FD, then ::handle::fd must be a valid file descriptor referencing a synchronization object. Ownership of the file descriptor is transferred to the CUDA driver when the handle is imported successfully. Performing any operations on the file descriptor after it is imported results in undefined behavior.

If ::type is EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32, then exactly one of ::handle::win32::handle and ::handle::win32::name must not be NULL. If ::handle::win32::handle is not NULL, then it must represent a valid shared NT handle that references a synchronization object. Ownership of this handle is not transferred to CUDA after the import operation, so the application must release the handle using the appropriate system call. If ::handle::win32::name is not NULL, then it must name a valid synchronization object.

If ::type is EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32_KMT, then ::handle::win32::handle must be non-NULL and ::handle::win32::name must be NULL. The handle specified must be a globally shared KMT handle. This handle does not hold a reference to the underlying object, and thus will be invalid when all references to the synchronization object are destroyed.

If ::type is EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D12_FENCE, then exactly one of ::handle::win32::handle and ::handle::win32::name must not be NULL. If ::handle::win32::handle is not NULL, then it must represent a valid shared NT handle that is returned by ID3D12Device::CreateSharedHandle when referring to a ID3D12Fence object. This handle holds a reference to the underlying object. If ::handle::win32::name is not NULL, then it must name a valid synchronization object that refers to a valid ID3D12Fence object.

If ::type is EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_FENCE, then ::handle::win32::handle represents a valid shared NT handle that is returned by ID3D11Fence::CreateSharedHandle. If ::handle::win32::name is not NULL, then it must name a valid synchronization object that refers to a valid ID3D11Fence object.

If ::type is EXTERNAL_SEMAPHORE_HANDLE_TYPE_NVSCISYNC, then ::handle::nvSciSyncObj represents a valid NvSciSyncObj.

EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEX, then ::handle::win32::handle represents a valid shared NT handle that is returned by IDXGIResource1::CreateSharedHandle when referring to a IDXGIKeyedMutex object. If ::handle::win32::name is not NULL, then it must name a valid synchronization object that refers to a valid IDXGIKeyedMutex object.

If ::type is EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEX_KMT, then ::handle::win32::handle represents a valid shared KMT handle that is returned by IDXGIResource::GetSharedHandle when referring to a IDXGIKeyedMutex object and ::handle::win32::name must be NULL.

If ::type is EXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_FD, then ::handle::fd must be a valid file descriptor referencing a synchronization object. Ownership of the file descriptor is transferred to the CUDA driver when the handle is imported successfully. Performing any operations on the file descriptor after it is imported results in undefined behavior.

If ::type is EXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_WIN32, then exactly one of ::handle::win32::handle and ::handle::win32::name must not be NULL. If ::handle::win32::handle is not NULL, then it must represent a valid shared NT handle that references a synchronization object. Ownership of this handle is not transferred to CUDA after the import operation, so the application must release the handle using the appropriate system call. If ::handle::win32::name is not NULL, then it must name a valid synchronization object.

Parameters:

extSem_out - returned handle to an external semaphore

semHandleDesc - semaphore import handle descriptor

ncuSignalExternalSemaphoresAsync

public static int ncuSignalExternalSemaphoresAsync(long extSemArray,
 long paramsArray,
 int numExtSems,
 long stream)

Unsafe version of: SignalExternalSemaphoresAsync

Parameters:

numExtSems - number of semaphores to signal

cuSignalExternalSemaphoresAsync

public static int cuSignalExternalSemaphoresAsync(PointerBuffer extSemArray,
 CUDA_EXTERNAL_SEMAPHORE_SIGNAL_PARAMS.Buffer paramsArray,
 long stream)

Signals a set of external semaphore objects,

Enqueues a signal operation on a set of externally allocated semaphore object in the specified stream. The operations will be executed when all prior operations in the stream complete.

The exact semantics of signaling a semaphore depends on the type of the object.

If the semaphore object is any one of the following types: EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_FD, EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32, EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32_KMT then signaling the semaphore will set it to the signaled state.

If the semaphore object is any one of the following types: EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D12_FENCE, EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_FENCE, EXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_FD, EXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_WIN32 then the semaphore will be set to the value specified in ::params::fence::value.

If the semaphore object is of the type EXTERNAL_SEMAPHORE_HANDLE_TYPE_NVSCISYNC this API sets ::params::nvSciSync::fence to a value that can be used by subsequent waiters of the same NvSciSync object to order operations with those currently submitted in stream. Such an update will overwrite previous contents of ::params::nvSciSync::fence. By default, signaling such an external semaphore object causes appropriate memory synchronization operations to be performed over all external memory objects that are imported as EXTERNAL_MEMORY_HANDLE_TYPE_NVSCIBUF. This ensures that any subsequent accesses made by other importers of the same set of NvSciBuf memory object(s) are coherent. These operations can be skipped by specifying the flag CUDA_EXTERNAL_SEMAPHORE_SIGNAL_SKIP_NVSCIBUF_MEMSYNC, which can be used as a performance optimization when data coherency is not required. But specifying this flag in scenarios where data coherency is required results in undefined behavior. Also, for semaphore object of the type EXTERNAL_SEMAPHORE_HANDLE_TYPE_NVSCISYNC, if the NvSciSyncAttrList used to create the NvSciSyncObj had not set the flags in DeviceGetNvSciSyncAttributes to CUDA_NVSCISYNC_ATTR_SIGNAL, this API will return CUDA_ERROR_NOT_SUPPORTED.

If the semaphore object is any one of the following types: EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEX, EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEX_KMT then the keyed mutex will be released with the key specified in ::params::keyedmutex::key.

Parameters:

extSemArray - set of external semaphores to be signaled

paramsArray - array of semaphore parameters

stream - stream to enqueue the signal operations in

ncuWaitExternalSemaphoresAsync

public static int ncuWaitExternalSemaphoresAsync(long extSemArray,
 long paramsArray,
 int numExtSems,
 long stream)

Unsafe version of: WaitExternalSemaphoresAsync

Parameters:

numExtSems - number of semaphores to wait on

cuWaitExternalSemaphoresAsync

public static int cuWaitExternalSemaphoresAsync(PointerBuffer extSemArray,
 CUDA_EXTERNAL_SEMAPHORE_WAIT_PARAMS.Buffer paramsArray,
 long stream)

Waits on a set of external semaphore objects.

Enqueues a wait operation on a set of externally allocated semaphore object in the specified stream. The operations will be executed when all prior operations in the stream complete.

The exact semantics of waiting on a semaphore depends on the type of the object.

If the semaphore object is any one of the following types: EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_FD, EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32, EXTERNAL_SEMAPHORE_HANDLE_TYPE_OPAQUE_WIN32_KMT then waiting on the semaphore will wait until the semaphore reaches the signaled state. The semaphore will then be reset to the unsignaled state. Therefore for every signal operation, there can only be one wait operation.

If the semaphore object is any one of the following types: EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D12_FENCE, EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_FENCE, EXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_FD, EXTERNAL_SEMAPHORE_HANDLE_TYPE_TIMELINE_SEMAPHORE_WIN32 then waiting on the semaphore will wait until the value of the semaphore is greater than or equal to ::params::fence::value.

If the semaphore object is of the type EXTERNAL_SEMAPHORE_HANDLE_TYPE_NVSCISYNC then, waiting on the semaphore will wait until the ::params::nvSciSync::fence is signaled by the signaler of the NvSciSyncObj that was associated with this semaphore object. By default, waiting on such an external semaphore object causes appropriate memory synchronization operations to be performed over all external memory objects that are imported as EXTERNAL_MEMORY_HANDLE_TYPE_NVSCIBUF. This ensures that any subsequent accesses made by other importers of the same set of NvSciBuf memory object(s) are coherent. These operations can be skipped by specifying the flag CUDA_EXTERNAL_SEMAPHORE_WAIT_SKIP_NVSCIBUF_MEMSYNC, which can be used as a performance optimization when data coherency is not required. But specifying this flag in scenarios where data coherency is required results in undefined behavior. Also, for semaphore object of the type EXTERNAL_SEMAPHORE_HANDLE_TYPE_NVSCISYNC, if the NvSciSyncAttrList used to create the NvSciSyncObj had not set the flags in DeviceGetNvSciSyncAttributes to CUDA_NVSCISYNC_ATTR_WAIT, this API will return CUDA_ERROR_NOT_SUPPORTED.

If the semaphore object is any one of the following types: EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEX, EXTERNAL_SEMAPHORE_HANDLE_TYPE_D3D11_KEYED_MUTEX_KMT then the keyed mutex will be acquired when it is released with the key specified in ::params::keyedmutex::key or until the timeout specified by ::params::keyedmutex::timeoutMs has lapsed. The timeout interval can either be a finite value specified in milliseconds or an infinite value. In case an infinite value is specified the timeout never elapses. The windows INFINITE macro must be used to specify infinite timeout.

Parameters:

extSemArray - external semaphores to be waited on

paramsArray - array of semaphore parameters

stream - stream to enqueue the wait operations in

cuDestroyExternalSemaphore

public static int cuDestroyExternalSemaphore(long extSem)

Destroys an external semaphore.

Destroys an external semaphore object and releases any references to the underlying resource. Any outstanding signals or waits must have completed before the semaphore is destroyed.

Parameters:

extSem - external semaphore to be destroyed

cuStreamWaitValue32

public static int cuStreamWaitValue32(long stream,
 long addr,
 int value,
 int flags)

Wait on a memory location.

Enqueues a synchronization of the stream on the given memory location. Work ordered after the operation will block until the given condition on the memory is satisfied. By default, the condition is to wait for (int32_t)(*addr - value) >= 0, a cyclic greater-or-equal. Other condition types can be specified via flags.

If the memory was registered via MemHostRegister, the device pointer should be obtained with MemHostGetDevicePointer. This function cannot be used with managed memory (MemAllocManaged).

Support for this can be queried with DeviceGetAttribute and DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS.

Support for STREAM_WAIT_VALUE_NOR can be queried with DeviceGetAttribute and DEVICE_ATTRIBUTE_CAN_USE_STREAM_WAIT_VALUE_NOR.

Parameters:

stream - the stream to synchronize on the memory location

addr - the memory location to wait on

value - the value to compare with the memory location

flags - see CUstreamWaitValue_flags

cuStreamWaitValue64

public static int cuStreamWaitValue64(long stream,
 long addr,
 long value,
 int flags)

Wait on a memory location.

Enqueues a synchronization of the stream on the given memory location. Work ordered after the operation will block until the given condition on the memory is satisfied. By default, the condition is to wait for (int64_t)(*addr - value) >= 0, a cyclic greater-or-equal. Other condition types can be specified via flags.

If the memory was registered via MemHostRegister, the device pointer should be obtained with MemHostGetDevicePointer.

Support for this can be queried with DeviceGetAttribute and DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS.

Parameters:

stream - the stream to synchronize on the memory location

addr - the memory location to wait on

value - the value to compare with the memory location

flags - see CUstreamWaitValue_flags

cuStreamWriteValue32

public static int cuStreamWriteValue32(long stream,
 long addr,
 int value,
 int flags)

Write a value to memory.

Write a value to memory. Unless the STREAM_WRITE_VALUE_NO_MEMORY_BARRIER flag is passed, the write is preceded by a system-wide memory fence, equivalent to a __threadfence_system() but scoped to the stream rather than a CUDA thread.

If the memory was registered via MemHostRegister, the device pointer should be obtained with MemHostGetDevicePointer. This function cannot be used with managed memory (MemAllocManaged).

Support for this can be queried with DeviceGetAttribute and DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS.

Parameters:

stream - the stream to do the write in

addr - the device address to write to

value - the value to write

flags - see CUstreamWriteValue_flags

cuStreamWriteValue64

public static int cuStreamWriteValue64(long stream,
 long addr,
 long value,
 int flags)

Write a value to memory.

Write a value to memory. Unless the STREAM_WRITE_VALUE_NO_MEMORY_BARRIER flag is passed, the write is preceded by a system-wide memory fence, equivalent to a __threadfence_system() but scoped to the stream rather than a CUDA thread.

If the memory was registered via MemHostRegister, the device pointer should be obtained with MemHostGetDevicePointer.

Support for this can be queried with DeviceGetAttribute and DEVICE_ATTRIBUTE_CAN_USE_64_BIT_STREAM_MEM_OPS.

Parameters:

stream - the stream to do the write in

addr - the device address to write to

value - the value to write

flags - see CUstreamWriteValue_flags

ncuStreamBatchMemOp

public static int ncuStreamBatchMemOp(long stream,
 int count,
 long paramArray,
 int flags)

Unsafe version of: StreamBatchMemOp

Parameters:

count - the number of operations in the array. Must be less than 256.

cuStreamBatchMemOp

public static int cuStreamBatchMemOp(long stream,
 CUstreamBatchMemOpParams.Buffer paramArray,
 int flags)

Batch operations to synchronize the stream via memory operations.

This is a batch version of StreamWaitValue32 and StreamWriteValue32. Batching operations may avoid some performance overhead in both the API call and the device execution versus adding them to the stream in separate API calls. The operations are enqueued in the order they appear in the array.

See CUstreamBatchMemOpType for the full set of supported operations, and StreamWaitValue32, StreamWaitValue64, StreamWriteValue32, and StreamWriteValue64 for details of specific operations.

Basic support for this can be queried with DeviceGetAttribute and DEVICE_ATTRIBUTE_CAN_USE_STREAM_MEM_OPS. See related APIs for details on querying support for specific operations.

Parameters:

stream - the stream to enqueue the operations in

paramArray - the types and parameters of the individual operations

flags - reserved for future expansion; must be 0

ncuFuncGetAttribute

public static int ncuFuncGetAttribute(long pi,
 int attrib,
 long hfunc)

Unsafe version of: FuncGetAttribute

cuFuncGetAttribute

public static int cuFuncGetAttribute(IntBuffer pi,
 int attrib,
 long hfunc)

Returns information about a function.

Returns in *pi the integer value of the attribute attrib on the kernel given by hfunc. The supported attributes are:

• FUNC_ATTRIBUTE_MAX_THREADS_PER_BLOCK: The maximum number of threads per block, beyond which a launch of the function would fail. This number depends on both the function and the device on which the function is currently loaded.
• FUNC_ATTRIBUTE_SHARED_SIZE_BYTES: The size in bytes of statically-allocated shared memory per block required by this function. This does not include dynamically-allocated shared memory requested by the user at runtime.
• FUNC_ATTRIBUTE_CONST_SIZE_BYTES: The size in bytes of user-allocated constant memory required by this function.
• FUNC_ATTRIBUTE_LOCAL_SIZE_BYTES: The size in bytes of local memory used by each thread of this function.
• FUNC_ATTRIBUTE_NUM_REGS: The number of registers used by each thread of this function.
• FUNC_ATTRIBUTE_PTX_VERSION: The PTX virtual architecture version for which the function was compiled. This value is the major PTX version * 10 + the minor PTX version, so a PTX version 1.3 function would return the value 13. Note that this may return the undefined value of 0 for cubins compiled prior to CUDA 3.0.
• FUNC_ATTRIBUTE_BINARY_VERSION: The binary architecture version for which the function was compiled. This value is the major binary version * 10 + the minor binary version, so a binary version 1.3 function would return the value 13. Note that this will return a value of 10 for legacy cubins that do not have a properly-encoded binary architecture version.
• FUNC_ATTRIBUTE_CACHE_MODE_CA: The attribute to indicate whether the function has been compiled with user specified option "-Xptxas --dlcm=ca" set.
• FUNC_ATTRIBUTE_MAX_DYNAMIC_SHARED_SIZE_BYTES: The maximum size in bytes of dynamically-allocated shared memory.
• FUNC_ATTRIBUTE_PREFERRED_SHARED_MEMORY_CARVEOUT: Preferred shared memory-L1 cache split ratio in percent of total shared memory.

Parameters:

pi - returned attribute value

attrib - attribute requested

hfunc - function to query attribute of

cuFuncSetAttribute

public static int cuFuncSetAttribute(long hfunc,
 int attrib,
 int value)

Sets information about a function.

This call sets the value of a specified attribute attrib on the kernel given by hfunc to an integer value specified by val This function returns CUDA_SUCCESS if the new value of the attribute could be successfully set. If the set fails, this call will return an error. Not all attributes can have values set. Attempting to set a value on a read-only attribute will result in an error (CUDA_ERROR_INVALID_VALUE).

Supported attributes for the cuFuncSetAttribute call are:

• FUNC_ATTRIBUTE_MAX_DYNAMIC_SHARED_SIZE_BYTES: This maximum size in bytes of dynamically-allocated shared memory. The value should contain the requested maximum size of dynamically-allocated shared memory. The sum of this value and the function attribute FUNC_ATTRIBUTE_SHARED_SIZE_BYTES cannot exceed the device attribute DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK_OPTIN. The maximal size of requestable dynamic shared memory may differ by GPU architecture.
• FUNC_ATTRIBUTE_PREFERRED_SHARED_MEMORY_CARVEOUT: On devices where the L1 cache and shared memory use the same hardware resources, this sets the shared memory carveout preference, in percent of the total shared memory. See DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR This is only a hint, and the driver can choose a different ratio if required to execute the function.

Parameters:

hfunc - function to query attribute of

attrib - attribute requested

value - the value to set

cuFuncSetCacheConfig

public static int cuFuncSetCacheConfig(long hfunc,
 int config)

Sets the preferred cache configuration for a device function.

On devices where the L1 cache and shared memory use the same hardware resources, this sets through config the preferred cache configuration for the device function hfunc. This is only a preference. The driver will use the requested configuration if possible, but it is free to choose a different configuration if required to execute hfunc. Any context-wide preference set via CtxSetCacheConfig will be overridden by this per-function setting unless the per-function setting is FUNC_CACHE_PREFER_NONE. In that case, the current context-wide setting will be used.

This setting does nothing on devices where the size of the L1 cache and shared memory are fixed.

Launching a kernel with a different preference than the most recent preference setting may insert a device-side synchronization point.

The supported cache configurations are:

• FUNC_CACHE_PREFER_NONE: no preference for shared memory or L1 (default)
• FUNC_CACHE_PREFER_SHARED: prefer larger shared memory and smaller L1 cache
• FUNC_CACHE_PREFER_L1: prefer larger L1 cache and smaller shared memory
• FUNC_CACHE_PREFER_EQUAL: prefer equal sized L1 cache and shared memory

Parameters:

hfunc - kernel to configure cache for

config - requested cache configuration

cuFuncSetSharedMemConfig

public static int cuFuncSetSharedMemConfig(long hfunc,
 int config)

Sets the shared memory configuration for a device function.

On devices with configurable shared memory banks, this function will force all subsequent launches of the specified device function to have the given shared memory bank size configuration. On any given launch of the function, the shared memory configuration of the device will be temporarily changed if needed to suit the function's preferred configuration. Changes in shared memory configuration between subsequent launches of functions, may introduce a device side synchronization point.

Any per-function setting of shared memory bank size set via FuncSetSharedMemConfig will override the context wide setting set with CtxSetSharedMemConfig.

Changing the shared memory bank size will not increase shared memory usage or affect occupancy of kernels, but may have major effects on performance. Larger bank sizes will allow for greater potential bandwidth to shared memory, but will change what kinds of accesses to shared memory will result in bank conflicts.

This function will do nothing on devices with fixed shared memory bank size.

The supported bank configurations are:

• SHARED_MEM_CONFIG_DEFAULT_BANK_SIZE: use the context's shared memory configuration when launching this function.
• SHARED_MEM_CONFIG_FOUR_BYTE_BANK_SIZE: set shared memory bank width to be natively four bytes when launching this function.
• SHARED_MEM_CONFIG_EIGHT_BYTE_BANK_SIZE: set shared memory bank width to be natively eight bytes when launching this function.

Parameters:

hfunc - kernel to be given a shared memory config

config - requested shared memory configuration

ncuFuncGetModule

public static int ncuFuncGetModule(long hmod,
 long hfunc)

Unsafe version of: FuncGetModule

cuFuncGetModule

public static int cuFuncGetModule(PointerBuffer hmod,
 long hfunc)

Returns a module handle.

Returns in *hmod the handle of the module that function hfunc is located in. The lifetime of the module corresponds to the lifetime of the context it was loaded in or until the module is explicitly unloaded.

The CUDA runtime manages its own modules loaded into the primary context. If the handle returned by this API refers to a module loaded by the CUDA runtime, calling ModuleUnload on that module will result in undefined behavior.

Parameters:

hmod - returned module handle

hfunc - function to retrieve module for

ncuLaunchKernel

public static int ncuLaunchKernel(long f,
 int gridDimX,
 int gridDimY,
 int gridDimZ,
 int blockDimX,
 int blockDimY,
 int blockDimZ,
 int sharedMemBytes,
 long hStream,
 long kernelParams,
 long extra)

Unsafe version of: LaunchKernel

cuLaunchKernel

public static int cuLaunchKernel(long f,
 int gridDimX,
 int gridDimY,
 int gridDimZ,
 int blockDimX,
 int blockDimY,
 int blockDimZ,
 int sharedMemBytes,
 long hStream,
 @Nullable
 PointerBuffer kernelParams,
 @Nullable
 PointerBuffer extra)

Launches a CUDA function.

Invokes the kernel f on a gridDimX x gridDimY x gridDimZ grid of blocks. Each block contains blockDimX x blockDimY x blockDimZ threads.

sharedMemBytes sets the amount of dynamic shared memory that will be available to each thread block.

Kernel parameters to f can be specified in one of two ways:

1. Kernel parameters can be specified via kernelParams.

   If f has N parameters, then kernelParams needs to be an array of N pointers. Each of kernelParams[0] through kernelParams[N-1] must point to a region of memory from which the actual kernel parameter will be copied. The number of kernel parameters and their offsets and sizes do not need to be specified as that information is retrieved directly from the kernel's image.

2. Kernel parameters can also be packaged by the application into a single buffer that is passed in via the extra parameter.

   This places the burden on the application of knowing each kernel parameter's size and alignment/padding within the buffer. Here is an example of using the extra parameter in this manner:

   
    size_t argBufferSize;
    char argBuffer[256];
    
    // populate argBuffer and argBufferSize
    
    void *config[] = {
        CU_LAUNCH_PARAM_BUFFER_POINTER, argBuffer,
        CU_LAUNCH_PARAM_BUFFER_SIZE,    &argBufferSize,
        CU_LAUNCH_PARAM_END
    };
    status = cuLaunchKernel(f, gx, gy, gz, bx, by, bz, sh, s, NULL, config);

The extra parameter exists to allow cuLaunchKernel() to take additional less commonly used arguments. extra specifies a list of names of extra settings and their corresponding values. Each extra setting name is immediately followed by the corresponding value. The list must be terminated with either NULL or LAUNCH_PARAM_END.

• LAUNCH_PARAM_END, which indicates the end of the extra array
• LAUNCH_PARAM_BUFFER_POINTER, which specifies that the next value in extra will be a pointer to a buffer containing all the kernel parameters for launching kernel f
• LAUNCH_PARAM_BUFFER_SIZE, which specifies that the next value in extra will be a pointer to a size_t containing the size of the buffer specified with LAUNCH_PARAM_BUFFER_POINTER

The error CUDA_ERROR_INVALID_VALUE will be returned if kernel parameters are specified with both kernelParams and extra (i.e. both kernelParams and extra are non-NULL).

Calling cuLaunchKernel() invalidates the persistent function state set through the following deprecated APIs: FuncSetBlockShape, FuncSetSharedSize, ParamSetSize, ParamSeti, ParamSetf, ParamSetv.

Note that to use LaunchKernel, the kernel f must either have been compiled with toolchain version 3.2 or later so that it will contain kernel parameter information, or have no kernel parameters. If either of these conditions is not met, then LaunchKernel will return CUDA_ERROR_INVALID_IMAGE.

Parameters:

f - kernel to launch

gridDimX - width of grid in blocks

gridDimY - height of grid in blocks

gridDimZ - depth of grid in blocks

blockDimX - x dimension of each thread block

blockDimY - y dimension of each thread block

blockDimZ - z dimension of each thread block

sharedMemBytes - dynamic shared-memory size per thread block in bytes

hStream - stream identifier

kernelParams - array of pointers to kernel parameters

extra - extra options

ncuLaunchCooperativeKernel

public static int ncuLaunchCooperativeKernel(long f,
 int gridDimX,
 int gridDimY,
 int gridDimZ,
 int blockDimX,
 int blockDimY,
 int blockDimZ,
 int sharedMemBytes,
 long hStream,
 long kernelParams)

Unsafe version of: LaunchCooperativeKernel

cuLaunchCooperativeKernel

public static int cuLaunchCooperativeKernel(long f,
 int gridDimX,
 int gridDimY,
 int gridDimZ,
 int blockDimX,
 int blockDimY,
 int blockDimZ,
 int sharedMemBytes,
 long hStream,
 @Nullable
 PointerBuffer kernelParams)

Launches a CUDA function where thread blocks can cooperate and synchronize as they execute.

Invokes the kernel f on a gridDimX x gridDimY x gridDimZ grid of blocks. Each block contains blockDimX x blockDimY x blockDimZ threads.

sharedMemBytes sets the amount of dynamic shared memory that will be available to each thread block.

The device on which this kernel is invoked must have a non-zero value for the device attribute DEVICE_ATTRIBUTE_COOPERATIVE_LAUNCH.

The total number of blocks launched cannot exceed the maximum number of blocks per multiprocessor as returned by OccupancyMaxActiveBlocksPerMultiprocessor (or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags) times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT.

The kernel cannot make use of CUDA dynamic parallelism.

Kernel parameters must be specified via kernelParams. If f has N parameters, then kernelParams needs to be an array of N pointers. Each of kernelParams[0] through kernelParams[N-1] must point to a region of memory from which the actual kernel parameter will be copied. The number of kernel parameters and their offsets and sizes do not need to be specified as that information is retrieved directly from the kernel's image.

Calling LaunchCooperativeKernel sets persistent function state that is the same as function state set through LaunchKernel API

When the kernel f is launched via LaunchCooperativeKernel, the previous block shape, shared size and parameter info associated with f is overwritten.

Note that to use LaunchCooperativeKernel, the kernel f must either have been compiled with toolchain version 3.2 or later so that it will contain kernel parameter information, or have no kernel parameters. If either of these conditions is not met, then LaunchCooperativeKernel will return CUDA_ERROR_INVALID_IMAGE.

Parameters:

f - kernel to launch

gridDimX - width of grid in blocks

gridDimY - height of grid in blocks

gridDimZ - depth of grid in blocks

blockDimX - x dimension of each thread block

blockDimY - y dimension of each thread block

blockDimZ - z dimension of each thread block

sharedMemBytes - dynamic shared-memory size per thread block in bytes

hStream - stream identifier

kernelParams - array of pointers to kernel parameters

ncuLaunchCooperativeKernelMultiDevice

public static int ncuLaunchCooperativeKernelMultiDevice(long launchParamsList,
 int numDevices,
 int flags)

Unsafe version of: LaunchCooperativeKernelMultiDevice

Parameters:

numDevices - size of the launchParamsList array

cuLaunchCooperativeKernelMultiDevice

public static int cuLaunchCooperativeKernelMultiDevice(CUDA_LAUNCH_PARAMS.Buffer launchParamsList,
 int flags)

Launches CUDA functions on multiple devices where thread blocks can cooperate and synchronize as they executeDeprecated: This function is deprecated as of CUDA 11.3.

Invokes kernels as specified in the launchParamsList array where each element of the array specifies all the parameters required to perform a single kernel launch. These kernels can cooperate and synchronize as they execute. The size of the array is specified by numDevices.

No two kernels can be launched on the same device. All the devices targeted by this multi-device launch must be identical. All devices must have a non-zero value for the device attribute DEVICE_ATTRIBUTE_COOPERATIVE_MULTI_DEVICE_LAUNCH.

All kernels launched must be identical with respect to the compiled code. Note that any __device__ __constant__ or __managed__ variables present in the module that owns the kernel launched on each device, are independently instantiated on every device. It is the application's responsibility to ensure these variables are initialized and used appropriately.

The size of the grids as specified in blocks, the size of the blocks themselves and the amount of shared memory used by each thread block must also match across all launched kernels.

The streams used to launch these kernels must have been created via either StreamCreate or StreamCreateWithPriority. The NULL stream or STREAM_LEGACY or STREAM_PER_THREAD cannot be used.

The total number of blocks launched per kernel cannot exceed the maximum number of blocks per multiprocessor as returned by OccupancyMaxActiveBlocksPerMultiprocessor (or OccupancyMaxActiveBlocksPerMultiprocessorWithFlags) times the number of multiprocessors as specified by the device attribute DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT. Since the total number of blocks launched per device has to match across all devices, the maximum number of blocks that can be launched per device will be limited by the device with the least number of multiprocessors.

The kernels cannot make use of CUDA dynamic parallelism.

• CUDA_LAUNCH_PARAMS::function specifies the kernel to be launched. All functions must be identical with respect to the compiled code.
• CUDA_LAUNCH_PARAMS::gridDimX is the width of the grid in blocks. This must match across all kernels launched.
• CUDA_LAUNCH_PARAMS::gridDimY is the height of the grid in blocks. This must match across all kernels launched.
• CUDA_LAUNCH_PARAMS::gridDimZ is the depth of the grid in blocks. This must match across all kernels launched.
• CUDA_LAUNCH_PARAMS::blockDimX is the X dimension of each thread block. This must match across all kernels launched.
• CUDA_LAUNCH_PARAMS::blockDimX is the Y dimension of each thread block. This must match across all kernels launched.
• CUDA_LAUNCH_PARAMS::blockDimZ is the Z dimension of each thread block. This must match across all kernels launched.
• CUDA_LAUNCH_PARAMS::sharedMemBytes is the dynamic shared-memory size per thread block in bytes. This must match across all kernels launched.
• CUDA_LAUNCH_PARAMS::hStream is the handle to the stream to perform the launch in. This cannot be the NULL stream or STREAM_LEGACY or STREAM_PER_THREAD. The CUDA context associated with this stream must match that associated with CUDA_LAUNCH_PARAMS::function.
• CUDA_LAUNCH_PARAMS::kernelParams is an array of pointers to kernel parameters. If ::function has N parameters, then ::kernelParams needs to be an array of N pointers. Each of ::kernelParams[0] through ::kernelParams[N-1] must point to a region of memory from which the actual kernel parameter will be copied. The number of kernel parameters and their offsets and sizes do not need to be specified as that information is retrieved directly from the kernel's image.

By default, the kernel won't begin execution on any GPU until all prior work in all the specified streams has completed. This behavior can be overridden by specifying the flag CUDA_COOPERATIVE_LAUNCH_MULTI_DEVICE_NO_PRE_LAUNCH_SYNC. When this flag is specified, each kernel will only wait for prior work in the stream corresponding to that GPU to complete before it begins execution.

Similarly, by default, any subsequent work pushed in any of the specified streams will not begin execution until the kernels on all GPUs have completed. This behavior can be overridden by specifying the flag CUDA_COOPERATIVE_LAUNCH_MULTI_DEVICE_NO_POST_LAUNCH_SYNC. When this flag is specified, any subsequent work pushed in any of the specified streams will only wait for the kernel launched on the GPU corresponding to that stream to complete before it begins execution.

Calling LaunchCooperativeKernelMultiDevice sets persistent function state that is the same as function state set through LaunchKernel API when called individually for each element in launchParamsList.

When kernels are launched via LaunchCooperativeKernelMultiDevice, the previous block shape, shared size and parameter info associated with each CUDA_LAUNCH_PARAMS::function in launchParamsList is overwritten.

Note that to use LaunchCooperativeKernelMultiDevice, the kernels must either have been compiled with toolchain version 3.2 or later so that it will contain kernel parameter information, or have no kernel parameters. If either of these conditions is not met, then LaunchCooperativeKernelMultiDevice will return CUDA_ERROR_INVALID_IMAGE.

Parameters:

launchParamsList - list of launch parameters, one per device

flags - flags to control launch behavior

ncuLaunchHostFunc

public static int ncuLaunchHostFunc(long hStream,
 long fn,
 long userData)

Unsafe version of: LaunchHostFunc

cuLaunchHostFunc

public static int cuLaunchHostFunc(long hStream,
 CUhostFnI fn,
 long userData)

Enqueues a host function call in a stream.

Enqueues a host function to run in a stream. The function will be called after currently enqueued work and will block work added after it.

The host function must not make any CUDA API calls. Attempting to use a CUDA API may result in CUDA_ERROR_NOT_PERMITTED, but this is not required. The host function must not perform any synchronization that may depend on outstanding CUDA work not mandated to run earlier. Host functions without a mandated order (such as in independent streams) execute in undefined order and may be serialized.

For the purposes of Unified Memory, execution makes a number of guarantees:

• The stream is considered idle for the duration of the function's execution. Thus, for example, the function may always use memory attached to the stream it was enqueued in.
• The start of execution of the function has the same effect as synchronizing an event recorded in the same stream immediately prior to the function. It thus synchronizes streams which have been "joined" prior to the function.
• Adding device work to any stream does not have the effect of making the stream active until all preceding host functions and stream callbacks have executed. Thus, for example, a function might use global attached memory even if work has been added to another stream, if the work has been ordered behind the function call with an event.
• Completion of the function does not cause a stream to become active except as described above. The stream will remain idle if no device work follows the function, and will remain idle across consecutive host functions or stream callbacks without device work in between. Thus, for example, stream synchronization can be done by signaling from a host function at the end of the stream.

Note that, in contrast to StreamAddCallback, the function will not be called in the event of an error in the CUDA context.

Parameters:

hStream - stream to enqueue function call in

fn - the function to call once preceding stream operations are complete

userData - user-specified data to be passed to the function

cuFuncSetBlockShape

public static int cuFuncSetBlockShape(long hfunc,
 int x,
 int y,
 int z)

Sets the block-dimensions for the function. (Deprecated)

Specifies the x, y, and z dimensions of the thread blocks that are created when the kernel given by hfunc is launched.

Parameters:

hfunc - kernel to specify dimensions of

x - x dimension

y - y dimension

z - z dimension

cuFuncSetSharedSize

public static int cuFuncSetSharedSize(long hfunc,
 int bytes)

Sets the dynamic shared-memory size for the function. (Deprecated)

Sets through bytes the amount of dynamic shared memory that will be available to each thread block when the kernel given by hfunc is launched.

Parameters:

hfunc - kernel to specify dynamic shared-memory size for

bytes - dynamic shared-memory size per thread in bytes

cuParamSetSize

public static int cuParamSetSize(long hfunc,
 int numbytes)

Sets the parameter size for the function. (Deprecated)

Sets through numbytes the total size in bytes needed by the function parameters of the kernel corresponding to hfunc.

Parameters:

hfunc - kernel to set parameter size for

numbytes - size of parameter list in bytes

cuParamSeti

public static int cuParamSeti(long hfunc,
 int offset,
 int value)

Adds an integer parameter to the function's argument listDeprecated:

Sets an integer parameter that will be specified the next time the kernel corresponding to hfunc will be invoked. offset is a byte offset.

Parameters:

hfunc - kernel to add parameter to

offset - offset to add parameter to argument list

value - value of parameter

cuParamSetf

public static int cuParamSetf(long hfunc,
 int offset,
 float value)

Adds a floating-point parameter to the function's argument list. (Deprecated)

Sets a floating-point parameter that will be specified the next time the kernel corresponding to hfunc will be invoked. offset is a byte offset.

Parameters:

hfunc - kernel to add parameter to

offset - offset to add parameter to argument list

value - value of parameter

ncuParamSetv

public static int ncuParamSetv(long hfunc,
 int offset,
 long ptr,
 int numbytes)

Unsafe version of: ParamSetv

Parameters:

numbytes - size of data to copy in bytes

cuParamSetv

public static int cuParamSetv(long hfunc,
 int offset,
 ByteBuffer ptr)

Adds arbitrary data to the function's argument list. (Deprecated)

Copies an arbitrary amount of data (specified in numbytes) from ptr into the parameter space of the kernel corresponding to hfunc. offset is a byte offset.

Parameters:

hfunc - kernel to add data to

offset - offset to add data to argument list

ptr - pointer to arbitrary data

cuLaunch

public static int cuLaunch(long f)

Launches a CUDA function. (Deprecated)

Invokes the kernel f on a 1 x 1 x 1 grid of blocks. The block contains the number of threads specified by a previous call to FuncSetBlockShape.

The block shape, dynamic shared memory size, and parameter information must be set using FuncSetBlockShape, FuncSetSharedSize, ParamSetSize, ParamSeti, ParamSetf, and ParamSetv prior to calling this function.

Launching a function via LaunchKernel invalidates the function's block shape, dynamic shared memory size, and parameter information. After launching via cuLaunchKernel, this state must be re-initialized prior to calling this function. Failure to do so results in undefined behavior.

Parameters:

f - kernel to launch

cuLaunchGrid

public static int cuLaunchGrid(long f,
 int grid_width,
 int grid_height)

Launches a CUDA function. (Deprecated)

Invokes the kernel f on a grid_width x grid_height grid of blocks. Each block contains the number of threads specified by a previous call to FuncSetBlockShape.

The block shape, dynamic shared memory size, and parameter information must be set using FuncSetBlockShape, FuncSetSharedSize, ParamSetSize, ParamSeti, ParamSetf, and ParamSetv prior to calling this function.

Launching a function via LaunchKernel invalidates the function's block shape, dynamic shared memory size, and parameter information. After launching via cuLaunchKernel, this state must be re-initialized prior to calling this function. Failure to do so results in undefined behavior.

Parameters:

f - kernel to launch

grid_width - width of grid in blocks

grid_height - height of grid in blocks

cuLaunchGridAsync

public static int cuLaunchGridAsync(long f,
 int grid_width,
 int grid_height,
 long hStream)

Launches a CUDA function. (Deprecated)

Invokes the kernel f on a grid_width x grid_height grid of blocks. Each block contains the number of threads specified by a previous call to FuncSetBlockShape.

The block shape, dynamic shared memory size, and parameter information must be set using FuncSetBlockShape, FuncSetSharedSize, ParamSetSize, ParamSeti, ParamSetf, and ParamSetv prior to calling this function.

Launching a function via LaunchKernel invalidates the function's block shape, dynamic shared memory size, and parameter information. After launching via cuLaunchKernel, this state must be re-initialized prior to calling this function. Failure to do so results in undefined behavior.

Note

In certain cases where cubins are created with no ABI (i.e., using ptxas --abi-compile no), this function may serialize kernel launches. The CUDA driver retains asynchronous behavior by growing the per-thread stack as needed per launch and not shrinking it afterwards.

Parameters:

f - kernel to launch

grid_width - width of grid in blocks

grid_height - height of grid in blocks

hStream - stream identifier

cuParamSetTexRef

public static int cuParamSetTexRef(long hfunc,
 int texunit,
 long hTexRef)

Adds a texture-reference to the function's argument list. (Deprecated)

Makes the CUDA array or linear memory bound to the texture reference hTexRef available to a device program as a texture. In this version of CUDA, the texture-reference must be obtained via ModuleGetTexRef and the texunit parameter must be set to PARAM_TR_DEFAULT.

Parameters:

hfunc - kernel to add texture-reference to

texunit - texture unit (must be PARAM_TR_DEFAULT)

hTexRef - texture-reference to add to argument list

ncuGraphCreate

public static int ncuGraphCreate(long phGraph,
 int flags)

Unsafe version of: GraphCreate

cuGraphCreate

public static int cuGraphCreate(PointerBuffer phGraph,
 int flags)

Creates a graph.

Creates an empty graph, which is returned via phGraph.

Parameters:

phGraph - returns newly created graph

flags - graph creation flags, must be 0

ncuGraphAddKernelNode

public static int ncuGraphAddKernelNode(long phGraphNode,
 long hGraph,
 long dependencies,
 long numDependencies,
 long nodeParams)

Unsafe version of: GraphAddKernelNode

Parameters:

numDependencies - number of dependencies

cuGraphAddKernelNode

public static int cuGraphAddKernelNode(PointerBuffer phGraphNode,
 long hGraph,
 @Nullable
 PointerBuffer dependencies,
 CUDA_KERNEL_NODE_PARAMS nodeParams)

Creates a kernel execution node and adds it to a graph.

Creates a new kernel execution node and adds it to hGraph with numDependencies dependencies specified via dependencies and arguments specified in nodeParams. It is possible for numDependencies to be 0, in which case the node will be placed at the root of the graph. dependencies may not have any duplicate entries. A handle to the new node will be returned in phGraphNode.

When the graph is launched, the node will invoke kernel func on a (gridDimX x gridDimY x gridDimZ) grid of blocks. Each block contains (blockDimX x blockDimY x blockDimZ) threads.

sharedMemBytes sets the amount of dynamic shared memory that will be available to each thread block.

Kernel parameters to func can be specified in one of two ways:

1. Kernel parameters can be specified via kernelParams. If the kernel has N parameters, then kernelParams needs to be an array of N pointers. Each pointer, from kernelParams[0] to kernelParams[N-1], points to the region of memory from which the actual parameter will be copied. The number of kernel parameters and their offsets and sizes do not need to be specified as that information is retrieved directly from the kernel's image.
2. Kernel parameters for non-cooperative kernels can also be packaged by the application into a single buffer that is passed in via extra. This places the burden on the application of knowing each kernel parameter's size and alignment/padding within the buffer. The extra parameter exists to allow this function to take additional less commonly used arguments. extra specifies a list of names of extra settings and their corresponding values. Each extra setting name is immediately followed by the corresponding value. The list must be terminated with either NULL or LAUNCH_PARAM_END.
   • LAUNCH_PARAM_END, which indicates the end of the extra array;
   • LAUNCH_PARAM_BUFFER_POINTER, which specifies that the next value in extra will be a pointer to a buffer containing all the kernel parameters for launching kernel func;
   • LAUNCH_PARAM_BUFFER_SIZE, which specifies that the next value in extra will be a pointer to a size_t containing the size of the buffer specified with LAUNCH_PARAM_BUFFER_POINTER;

The error CUDA_ERROR_INVALID_VALUE will be returned if kernel parameters are specified with both kernelParams and extra (i.e. both kernelParams and extra are non-NULL). CUDA_ERROR_INVALID_VALUE will be returned if extra is used for a cooperative kernel.

The kernelParams or extra array, as well as the argument values it points to, are copied during this call.

Note

Kernels launched using graphs must not use texture and surface references. Reading or writing through any texture or surface reference is undefined behavior. This restriction does not apply to texture and surface objects.

Parameters:

phGraphNode - returns newly created node

hGraph - graph to which to add the node

dependencies - dependencies of the node

nodeParams - parameters for the GPU execution node

ncuGraphKernelNodeGetParams

public static int ncuGraphKernelNodeGetParams(long hNode,
 long nodeParams)

Unsafe version of: GraphKernelNodeGetParams

cuGraphKernelNodeGetParams

public static int cuGraphKernelNodeGetParams(long hNode,
 CUDA_KERNEL_NODE_PARAMS nodeParams)

Returns a kernel node's parameters.

Returns the parameters of kernel node hNode in nodeParams. The kernelParams or extra array returned in nodeParams, as well as the argument values it points to, are owned by the node. This memory remains valid until the node is destroyed or its parameters are modified, and should not be modified directly. Use GraphKernelNodeSetParams to update the parameters of this node.

The params will contain either kernelParams or extra, according to which of these was most recently set on the node.

Parameters:

hNode - node to get the parameters for

nodeParams - pointer to return the parameters

ncuGraphKernelNodeSetParams

public static int ncuGraphKernelNodeSetParams(long hNode,
 long nodeParams)

Unsafe version of: GraphKernelNodeSetParams

cuGraphKernelNodeSetParams

public static int cuGraphKernelNodeSetParams(long hNode,
 CUDA_KERNEL_NODE_PARAMS nodeParams)

Sets a kernel node's parameters.

Sets the parameters of kernel node hNode to nodeParams.

Parameters:

hNode - node to set the parameters for

nodeParams - parameters to copy

ncuGraphAddMemcpyNode

public static int ncuGraphAddMemcpyNode(long phGraphNode,
 long hGraph,
 long dependencies,
 long numDependencies,
 long copyParams,
 long ctx)

Unsafe version of: GraphAddMemcpyNode

Parameters:

numDependencies - number of dependencies

cuGraphAddMemcpyNode

public static int cuGraphAddMemcpyNode(PointerBuffer phGraphNode,
 long hGraph,
 @Nullable
 PointerBuffer dependencies,
 CUDA_MEMCPY3D copyParams,
 long ctx)

Creates a memcpy node and adds it to a graph.

Creates a new memcpy node and adds it to hGraph with numDependencies dependencies specified via dependencies. It is possible for numDependencies to be 0, in which case the node will be placed at the root of the graph. dependencies may not have any duplicate entries. A handle to the new node will be returned in phGraphNode.

When the graph is launched, the node will perform the memcpy described by copyParams. See Memcpy3D for a description of the structure and its restrictions.

Memcpy nodes have some additional restrictions with regards to managed memory, if the system contains at least one device which has a zero value for the device attribute DEVICE_ATTRIBUTE_CONCURRENT_MANAGED_ACCESS. If one or more of the operands refer to managed memory, then using the memory type MEMORYTYPE_UNIFIED is disallowed for those operand(s). The managed memory will be treated as residing on either the host or the device, depending on which memory type is specified.

Parameters:

phGraphNode - returns newly created node

hGraph - graph to which to add the node

dependencies - dependencies of the node

copyParams - parameters for the memory copy

ctx - context on which to run the node

ncuGraphMemcpyNodeGetParams

public static int ncuGraphMemcpyNodeGetParams(long hNode,
 long nodeParams)

Unsafe version of: GraphMemcpyNodeGetParams

cuGraphMemcpyNodeGetParams

public static int cuGraphMemcpyNodeGetParams(long hNode,
 CUDA_MEMCPY3D nodeParams)

Returns a memcpy node's parameters.

Returns the parameters of memcpy node hNode in nodeParams.

Parameters:

hNode - node to get the parameters for

nodeParams - pointer to return the parameters

ncuGraphMemcpyNodeSetParams

public static int ncuGraphMemcpyNodeSetParams(long hNode,
 long nodeParams)

Unsafe version of: GraphMemcpyNodeSetParams

cuGraphMemcpyNodeSetParams

public static int cuGraphMemcpyNodeSetParams(long hNode,
 CUDA_MEMCPY3D nodeParams)

Sets a memcpy node's parameters.

Sets the parameters of memcpy node hNode to nodeParams.

Parameters:

hNode - node to set the parameters for

nodeParams - parameters to copy

ncuGraphAddMemsetNode

public static int ncuGraphAddMemsetNode(long phGraphNode,
 long hGraph,
 long dependencies,
 long numDependencies,
 long memsetParams,
 long ctx)

Unsafe version of: GraphAddMemsetNode

Parameters:

numDependencies - number of dependencies

cuGraphAddMemsetNode

public static int cuGraphAddMemsetNode(PointerBuffer phGraphNode,
 long hGraph,
 @Nullable
 PointerBuffer dependencies,
 CUDA_MEMSET_NODE_PARAMS memsetParams,
 long ctx)

Creates a memset node and adds it to a graph.

Creates a new memset node and adds it to hGraph with numDependencies dependencies specified via dependencies. It is possible for numDependencies to be 0, in which case the node will be placed at the root of the graph. dependencies may not have any duplicate entries. A handle to the new node will be returned in phGraphNode.

The element size must be 1, 2, or 4 bytes. When the graph is launched, the node will perform the memset described by memsetParams.

Parameters:

phGraphNode - returns newly created node

hGraph - graph to which to add the node

dependencies - dependencies of the node

memsetParams - parameters for the memory set

ctx - context on which to run the node

ncuGraphMemsetNodeGetParams

public static int ncuGraphMemsetNodeGetParams(long hNode,
 long nodeParams)

Unsafe version of: GraphMemsetNodeGetParams

cuGraphMemsetNodeGetParams

public static int cuGraphMemsetNodeGetParams(long hNode,
 CUDA_MEMSET_NODE_PARAMS nodeParams)

Returns a memset node's parameters.

Returns the parameters of memset node hNode in nodeParams.

Parameters:

hNode - node to get the parameters for

nodeParams - pointer to return the parameters

ncuGraphMemsetNodeSetParams

public static int ncuGraphMemsetNodeSetParams(long hNode,
 long nodeParams)

Unsafe version of: GraphMemsetNodeSetParams

cuGraphMemsetNodeSetParams

public static int cuGraphMemsetNodeSetParams(long hNode,
 CUDA_MEMSET_NODE_PARAMS nodeParams)

Sets a memset node's parameters.

Sets the parameters of memset node hNode to nodeParams.

Parameters:

hNode - node to set the parameters for

nodeParams - parameters to copy

ncuGraphAddHostNode

public static int ncuGraphAddHostNode(long phGraphNode,
 long hGraph,
 long dependencies,
 long numDependencies,
 long nodeParams)

Unsafe version of: GraphAddHostNode

Parameters:

numDependencies - number of dependencies

cuGraphAddHostNode

public static int cuGraphAddHostNode(PointerBuffer phGraphNode,
 long hGraph,
 @Nullable
 PointerBuffer dependencies,
 CUDA_HOST_NODE_PARAMS nodeParams)

Creates a host execution node and adds it to a graph.

Creates a new CPU execution node and adds it to hGraph with numDependencies dependencies specified via dependencies and arguments specified in nodeParams. It is possible for numDependencies to be 0, in which case the node will be placed at the root of the graph. dependencies may not have any duplicate entries. A handle to the new node will be returned in phGraphNode.

When the graph is launched, the node will invoke the specified CPU function. Host nodes are not supported under MPS with pre-Volta GPUs.

Parameters:

phGraphNode - returns newly created node

hGraph - graph to which to add the node

dependencies - dependencies of the node

nodeParams - parameters for the host node

ncuGraphHostNodeGetParams

public static int ncuGraphHostNodeGetParams(long hNode,
 long nodeParams)

Unsafe version of: GraphHostNodeGetParams

cuGraphHostNodeGetParams

public static int cuGraphHostNodeGetParams(long hNode,
 CUDA_HOST_NODE_PARAMS nodeParams)

Returns a host node's parameters.

Returns the parameters of host node hNode in nodeParams.

Parameters:

hNode - node to get the parameters for

nodeParams - pointer to return the parameters

ncuGraphHostNodeSetParams

public static int ncuGraphHostNodeSetParams(long hNode,
 long nodeParams)

Unsafe version of: GraphHostNodeSetParams

cuGraphHostNodeSetParams

public static int cuGraphHostNodeSetParams(long hNode,
 CUDA_HOST_NODE_PARAMS nodeParams)

Sets a host node's parameters.

Sets the parameters of host node hNode to nodeParams.

Parameters:

hNode - node to set the parameters for

nodeParams - parameters to copy

ncuGraphAddChildGraphNode

public static int ncuGraphAddChildGraphNode(long phGraphNode,
 long hGraph,
 long dependencies,
 long numDependencies,
 long childGraph)

Unsafe version of: GraphAddChildGraphNode

Parameters:

numDependencies - number of dependencies

cuGraphAddChildGraphNode

public static int cuGraphAddChildGraphNode(PointerBuffer phGraphNode,
 long hGraph,
 @Nullable
 PointerBuffer dependencies,
 long childGraph)

Creates a child graph node and adds it to a graph.

Creates a new node which executes an embedded graph, and adds it to hGraph with numDependencies dependencies specified via dependencies. It is possible for numDependencies to be 0, in which case the node will be placed at the root of the graph. dependencies may not have any duplicate entries. A handle to the new node will be returned in phGraphNode.

If hGraph contains allocation or free nodes, this call will return an error.

The node executes an embedded child graph. The child graph is cloned in this call.

Parameters:

phGraphNode - returns newly created node

hGraph - graph to which to add the node

dependencies - dependencies of the node

childGraph - the graph to clone into this node

ncuGraphChildGraphNodeGetGraph

public static int ncuGraphChildGraphNodeGetGraph(long hNode,
 long phGraph)

Unsafe version of: GraphChildGraphNodeGetGraph

cuGraphChildGraphNodeGetGraph

public static int cuGraphChildGraphNodeGetGraph(long hNode,
 PointerBuffer phGraph)

Gets a handle to the embedded graph of a child graph node.

Gets a handle to the embedded graph in a child graph node. This call does not clone the graph. Changes to the graph will be reflected in the node, and the node retains ownership of the graph.

Allocation and free nodes cannot be added to the returned graph. Attempting to do so will return an error.

Parameters:

hNode - node to get the embedded graph for

phGraph - location to store a handle to the graph

ncuGraphAddEmptyNode

public static int ncuGraphAddEmptyNode(long phGraphNode,
 long hGraph,
 long dependencies,
 long numDependencies)

Unsafe version of: GraphAddEmptyNode

Parameters:

numDependencies - number of dependencies

cuGraphAddEmptyNode

public static int cuGraphAddEmptyNode(PointerBuffer phGraphNode,
 long hGraph,
 @Nullable
 PointerBuffer dependencies)

Creates an empty node and adds it to a graph.

Creates a new node which performs no operation, and adds it to hGraph with numDependencies dependencies specified via dependencies. It is possible for numDependencies to be 0, in which case the node will be placed at the root of the graph. dependencies may not have any duplicate entries. A handle to the new node will be returned in phGraphNode.

An empty node performs no operation during execution, but can be used for transitive ordering. For example, a phased execution graph with 2 groups of n nodes with a barrier between them can be represented using an empty node and 2*n dependency edges, rather than no empty node and n^2 dependency edges.

Parameters:

phGraphNode - returns newly created node

hGraph - graph to which to add the node

dependencies - dependencies of the node

ncuGraphAddEventRecordNode

public static int ncuGraphAddEventRecordNode(long phGraphNode,
 long hGraph,
 long dependencies,
 long numDependencies,
 long event)

Unsafe version of: GraphAddEventRecordNode

Parameters:

numDependencies - number of dependencies

cuGraphAddEventRecordNode

public static int cuGraphAddEventRecordNode(PointerBuffer phGraphNode,
 long hGraph,
 @Nullable
 PointerBuffer dependencies,
 long event)

Creates an event record node and adds it to a graph.

Creates a new event record node and adds it to hGraph with numDependencies dependencies specified via dependencies and event specified in event. It is possible for numDependencies to be 0, in which case the node will be placed at the root of the graph. dependencies may not have any duplicate entries. A handle to the new node will be returned in phGraphNode.

Each launch of the graph will record event to capture execution of the node's dependencies.

Parameters:

phGraphNode - returns newly created node

hGraph - graph to which to add the node

dependencies - dependencies of the node

event - event for the node

ncuGraphEventRecordNodeGetEvent

public static int ncuGraphEventRecordNodeGetEvent(long hNode,
 long event_out)

Unsafe version of: GraphEventRecordNodeGetEvent

cuGraphEventRecordNodeGetEvent

public static int cuGraphEventRecordNodeGetEvent(long hNode,
 PointerBuffer event_out)

Returns the event associated with an event record node.

Returns the event of event record node hNode in event_out.

Parameters:

hNode - node to get the event for

event_out - pointer to return the event

cuGraphEventRecordNodeSetEvent

public static int cuGraphEventRecordNodeSetEvent(long hNode,
 long event)

Sets an event record node's event.

Sets the event of event record node hNode to event.

Parameters:

hNode - node to set the event for

event - event to use

ncuGraphAddEventWaitNode

public static int ncuGraphAddEventWaitNode(long phGraphNode,
 long hGraph,
 long dependencies,
 long numDependencies,
 long event)

Unsafe version of: GraphAddEventWaitNode

Parameters:

numDependencies - number of dependencies

cuGraphAddEventWaitNode

public static int cuGraphAddEventWaitNode(PointerBuffer phGraphNode,
 long hGraph,
 @Nullable
 PointerBuffer dependencies,
 long event)

Creates an event wait node and adds it to a graph.

Creates a new event wait node and adds it to hGraph with numDependencies dependencies specified via dependencies and event specified in event. It is possible for numDependencies to be 0, in which case the node will be placed at the root of the graph. dependencies may not have any duplicate entries. A handle to the new node will be returned in phGraphNode.

The graph node will wait for all work captured in event. See EventRecord for details on what is captured by an event. event may be from a different context or device than the launch stream.

Parameters:

phGraphNode - returns newly created node

hGraph - graph to which to add the node

dependencies - dependencies of the node

event - event for the node

ncuGraphEventWaitNodeGetEvent

public static int ncuGraphEventWaitNodeGetEvent(long hNode,
 long event_out)

Unsafe version of: GraphEventWaitNodeGetEvent

cuGraphEventWaitNodeGetEvent

public static int cuGraphEventWaitNodeGetEvent(long hNode,
 PointerBuffer event_out)

Returns the event associated with an event wait node.

Returns the event of event wait node hNode in event_out.

Parameters:

hNode - node to get the event for

event_out - pointer to return the event

cuGraphEventWaitNodeSetEvent

public static int cuGraphEventWaitNodeSetEvent(long hNode,
 long event)

Sets an event wait node's event.

Sets the event of event wait node hNode to event.

Parameters:

hNode - node to set the event for

event - event to use

ncuGraphAddExternalSemaphoresSignalNode

public static int ncuGraphAddExternalSemaphoresSignalNode(long phGraphNode,
 long hGraph,
 long dependencies,
 long numDependencies,
 long nodeParams)

Unsafe version of: GraphAddExternalSemaphoresSignalNode

Parameters:

numDependencies - number of dependencies

cuGraphAddExternalSemaphoresSignalNode

public static int cuGraphAddExternalSemaphoresSignalNode(PointerBuffer phGraphNode,
 long hGraph,
 @Nullable
 PointerBuffer dependencies,
 CUDA_EXT_SEM_SIGNAL_NODE_PARAMS nodeParams)

Creates an external semaphore signal node and adds it to a graph.

Creates a new external semaphore signal node and adds it to hGraph with numDependencies dependencies specified via dependencies and arguments specified in nodeParams. It is possible for numDependencies to be 0, in which case the node will be placed at the root of the graph. dependencies may not have any duplicate entries. A handle to the new node will be returned in phGraphNode.

Performs a signal operation on a set of externally allocated semaphore objects when the node is launched. The operation(s) will occur after all of the node's dependencies have completed.

Parameters:

phGraphNode - returns newly created node

hGraph - graph to which to add the node

dependencies - dependencies of the node

nodeParams - parameters for the node

ncuGraphExternalSemaphoresSignalNodeGetParams

public static int ncuGraphExternalSemaphoresSignalNodeGetParams(long hNode,
 long params_out)

Unsafe version of: GraphExternalSemaphoresSignalNodeGetParams

cuGraphExternalSemaphoresSignalNodeGetParams

public static int cuGraphExternalSemaphoresSignalNodeGetParams(long hNode,
 CUDA_EXT_SEM_SIGNAL_NODE_PARAMS params_out)

Returns an external semaphore signal node's parameters.

Returns the parameters of an external semaphore signal node hNode in params_out. The extSemArray and paramsArray returned in params_out, are owned by the node. This memory remains valid until the node is destroyed or its parameters are modified, and should not be modified directly. Use GraphExternalSemaphoresSignalNodeSetParams to update the parameters of this node.

Parameters:

hNode - node to get the parameters for

params_out - pointer to return the parameters

ncuGraphExternalSemaphoresSignalNodeSetParams

public static int ncuGraphExternalSemaphoresSignalNodeSetParams(long hNode,
 long nodeParams)

Unsafe version of: GraphExternalSemaphoresSignalNodeSetParams

cuGraphExternalSemaphoresSignalNodeSetParams

public static int cuGraphExternalSemaphoresSignalNodeSetParams(long hNode,
 CUDA_EXT_SEM_SIGNAL_NODE_PARAMS nodeParams)

Sets an external semaphore signal node's parameters.

Sets the parameters of an external semaphore signal node hNode to nodeParams.

Parameters:

hNode - node to set the parameters for

nodeParams - parameters to copy

ncuGraphAddExternalSemaphoresWaitNode

public static int ncuGraphAddExternalSemaphoresWaitNode(long phGraphNode,
 long hGraph,
 long dependencies,
 long numDependencies,
 long nodeParams)

Unsafe version of: GraphAddExternalSemaphoresWaitNode

Parameters:

numDependencies - number of dependencies

cuGraphAddExternalSemaphoresWaitNode

public static int cuGraphAddExternalSemaphoresWaitNode(PointerBuffer phGraphNode,
 long hGraph,
 @Nullable
 PointerBuffer dependencies,
 CUDA_EXT_SEM_WAIT_NODE_PARAMS nodeParams)

Creates an external semaphore wait node and adds it to a graph.

Creates a new external semaphore wait node and adds it to hGraph with numDependencies dependencies specified via dependencies and arguments specified in nodeParams. It is possible for numDependencies to be 0, in which case the node will be placed at the root of the graph. dependencies may not have any duplicate entries. A handle to the new node will be returned in phGraphNode.

Performs a wait operation on a set of externally allocated semaphore objects when the node is launched. The node's dependencies will not be launched until the wait operation has completed.

Parameters:

phGraphNode - returns newly created node

hGraph - graph to which to add the node

dependencies - dependencies of the node

nodeParams - parameters for the node

ncuGraphExternalSemaphoresWaitNodeGetParams

public static int ncuGraphExternalSemaphoresWaitNodeGetParams(long hNode,
 long params_out)

Unsafe version of: GraphExternalSemaphoresWaitNodeGetParams

cuGraphExternalSemaphoresWaitNodeGetParams

public static int cuGraphExternalSemaphoresWaitNodeGetParams(long hNode,
 CUDA_EXT_SEM_WAIT_NODE_PARAMS params_out)

Returns an external semaphore wait node's parameters.

Returns the parameters of an external semaphore wait node hNode in params_out. The extSemArray and paramsArray returned in params_out, are owned by the node. This memory remains valid until the node is destroyed or its parameters are modified, and should not be modified directly. Use GraphExternalSemaphoresSignalNodeSetParams to update the parameters of this node.

Parameters:

hNode - node to get the parameters for

params_out - pointer to return the parameters

ncuGraphExternalSemaphoresWaitNodeSetParams

public static int ncuGraphExternalSemaphoresWaitNodeSetParams(long hNode,
 long nodeParams)

Unsafe version of: GraphExternalSemaphoresWaitNodeSetParams

cuGraphExternalSemaphoresWaitNodeSetParams

public static int cuGraphExternalSemaphoresWaitNodeSetParams(long hNode,
 CUDA_EXT_SEM_WAIT_NODE_PARAMS nodeParams)

Sets an external semaphore wait node's parameters.

Sets the parameters of an external semaphore wait node hNode to nodeParams.

Parameters:

hNode - node to set the parameters for

nodeParams - parameters to copy

ncuGraphAddMemAllocNode

public static int ncuGraphAddMemAllocNode(long phGraphNode,
 long hGraph,
 long dependencies,
 long numDependencies,
 long nodeParams)

Unsafe version of: GraphAddMemAllocNode

Parameters:

numDependencies - number of dependencies

cuGraphAddMemAllocNode

public static int cuGraphAddMemAllocNode(PointerBuffer phGraphNode,
 long hGraph,
 @Nullable
 PointerBuffer dependencies,
 CUDA_MEM_ALLOC_NODE_PARAMS nodeParams)

Creates an allocation node and adds it to a graph.

Creates a new allocation node and adds it to hGraph with numDependencies dependencies specified via dependencies and arguments specified in nodeParams. It is possible for numDependencies to be 0, in which case the node will be placed at the root of the graph. dependencies may not have any duplicate entries. A handle to the new node will be returned in phGraphNode.

When GraphAddMemAllocNode creates an allocation node, it returns the address of the allocation in nodeParams.dptr. The allocation's address remains fixed across instantiations and launches.

If the allocation is freed in the same graph, by creating a free node using GraphAddMemFreeNode, the allocation can be accessed by nodes ordered after the allocation node but before the free node. These allocations cannot be freed outside the owning graph, and they can only be freed once in the owning graph.

If the allocation is not freed in the same graph, then it can be accessed not only by nodes in the graph which are ordered after the allocation node, but also by stream operations ordered after the graph's execution but before the allocation is freed.

Allocations which are not freed in the same graph can be freed by:

• passing the allocation to MemFreeAsync or MemFree;
• launching a graph with a free node for that allocation; or
• specifying CUDA_GRAPH_INSTANTIATE_FLAG_AUTO_FREE_ON_LAUNCH during instantiation, which makes each launch behave as though it called MemFreeAsync for every unfreed allocation.

It is not possible to free an allocation in both the owning graph and another graph. If the allocation is freed in the same graph, a free node cannot be added to another graph. If the allocation is freed in another graph, a free node can no longer be added to the owning graph.

The following restrictions apply to graphs which contain allocation and/or memory free nodes:

• Nodes and edges of the graph cannot be deleted.
• The graph cannot be used in a child node.
• Only one instantiation of the graph may exist at any point in time.
• The graph cannot be cloned.

Parameters:

phGraphNode - returns newly created node

hGraph - graph to which to add the node

dependencies - dependencies of the node

nodeParams - parameters for the node

ncuGraphMemAllocNodeGetParams

public static int ncuGraphMemAllocNodeGetParams(long hNode,
 long params_out)

Unsafe version of: GraphMemAllocNodeGetParams

cuGraphMemAllocNodeGetParams

public static int cuGraphMemAllocNodeGetParams(long hNode,
 CUDA_MEM_ALLOC_NODE_PARAMS params_out)

Returns a memory alloc node's parameters.

Returns the parameters of a memory alloc node hNode in params_out. The poolProps and accessDescs returned in params_out, are owned by the node. This memory remains valid until the node is destroyed. The returned parameters must not be modified.

Parameters:

hNode - node to get the parameters for

params_out - pointer to return the parameters

ncuGraphAddMemFreeNode

public static int ncuGraphAddMemFreeNode(long phGraphNode,
 long hGraph,
 long dependencies,
 long numDependencies,
 long dptr)

Unsafe version of: GraphAddMemFreeNode

Parameters:

numDependencies - number of dependencies

cuGraphAddMemFreeNode

public static int cuGraphAddMemFreeNode(PointerBuffer phGraphNode,
 long hGraph,
 @Nullable
 PointerBuffer dependencies,
 long dptr)

Creates a memory free node and adds it to a graph.

Creates a new memory free node and adds it to hGraph with numDependencies dependencies specified via dependencies and arguments specified in nodeParams. It is possible for numDependencies to be 0, in which case the node will be placed at the root of the graph. dependencies may not have any duplicate entries. A handle to the new node will be returned in phGraphNode.

GraphAddMemFreeNode will return CUDA_ERROR_INVALID_VALUE if the user attempts to free:

• an allocation twice in the same graph.
• an address that was not returned by an allocation node.
• an invalid address.

The following restrictions apply to graphs which contain allocation and/or memory free nodes:

• Nodes and edges of the graph cannot be deleted.
• The graph cannot be used in a child node.
• Only one instantiation of the graph may exist at any point in time.
• The graph cannot be cloned.

Parameters:

phGraphNode - returns newly created node

hGraph - graph to which to add the node

dependencies - dependencies of the node

dptr - address of memory to free

ncuGraphMemFreeNodeGetParams

public static int ncuGraphMemFreeNodeGetParams(long hNode,
 long dptr_out)

Unsafe version of: GraphMemFreeNodeGetParams

cuGraphMemFreeNodeGetParams

public static int cuGraphMemFreeNodeGetParams(long hNode,
 PointerBuffer dptr_out)

Returns a memory free node's parameters.

Returns the address of a memory free node hNode in dptr_out.

Parameters:

hNode - node to get the parameters for

dptr_out - pointer to return the device address

cuDeviceGraphMemTrim

public static int cuDeviceGraphMemTrim(int device)

Free unused memory that was cached on the specified device for use with graphs back to the OS.

Blocks which are not in use by a graph that is either currently executing or scheduled to execute are freed back to the operating system.

Parameters:

device - the device for which cached memory should be freed

ncuDeviceGetGraphMemAttribute

public static int ncuDeviceGetGraphMemAttribute(int device,
 int attr,
 long value)

Unsafe version of: DeviceGetGraphMemAttribute

cuDeviceGetGraphMemAttribute

public static int cuDeviceGetGraphMemAttribute(int device,
 int attr,
 ByteBuffer value)

Query asynchronous allocation attributes related to graphs.

Valid attributes are:

• GRAPH_MEM_ATTR_USED_MEM_CURRENT: Amount of memory, in bytes, currently associated with graphs
• GRAPH_MEM_ATTR_USED_MEM_HIGH: High watermark of memory, in bytes, associated with graphs since the last time it was reset. High watermark can only be reset to zero.
• GRAPH_MEM_ATTR_RESERVED_MEM_CURRENT: Amount of memory, in bytes, currently allocated for use by the CUDA graphs asynchronous allocator.
• GRAPH_MEM_ATTR_RESERVED_MEM_HIGH: High watermark of memory, in bytes, currently allocated for use by the CUDA graphs asynchronous allocator.

Parameters:

device - specifies the scope of the query

attr - attribute to get

value - retrieved value

cuDeviceGetGraphMemAttribute

public static int cuDeviceGetGraphMemAttribute(int device,
 int attr,
 LongBuffer value)

Query asynchronous allocation attributes related to graphs.

Valid attributes are:

• GRAPH_MEM_ATTR_USED_MEM_CURRENT: Amount of memory, in bytes, currently associated with graphs
• GRAPH_MEM_ATTR_USED_MEM_HIGH: High watermark of memory, in bytes, associated with graphs since the last time it was reset. High watermark can only be reset to zero.
• GRAPH_MEM_ATTR_RESERVED_MEM_CURRENT: Amount of memory, in bytes, currently allocated for use by the CUDA graphs asynchronous allocator.
• GRAPH_MEM_ATTR_RESERVED_MEM_HIGH: High watermark of memory, in bytes, currently allocated for use by the CUDA graphs asynchronous allocator.

Parameters:

device - specifies the scope of the query

attr - attribute to get

value - retrieved value

ncuDeviceSetGraphMemAttribute

public static int ncuDeviceSetGraphMemAttribute(int device,
 int attr,
 long value)

Unsafe version of: DeviceSetGraphMemAttribute

cuDeviceSetGraphMemAttribute

public static int cuDeviceSetGraphMemAttribute(int device,
 int attr,
 ByteBuffer value)

Set asynchronous allocation attributes related to graphs.

Valid attributes are:

• GRAPH_MEM_ATTR_USED_MEM_HIGH: High watermark of memory, in bytes, associated with graphs since the last time it was reset. High watermark can only be reset to zero.
• GRAPH_MEM_ATTR_RESERVED_MEM_HIGH: High watermark of memory, in bytes, currently allocated for use by the CUDA graphs asynchronous allocator.

Parameters:

device - specifies the scope of the query

attr - attribute to get

value - pointer to value to set

cuDeviceSetGraphMemAttribute

public static int cuDeviceSetGraphMemAttribute(int device,
 int attr,
 LongBuffer value)

Set asynchronous allocation attributes related to graphs.

Valid attributes are:

• GRAPH_MEM_ATTR_USED_MEM_HIGH: High watermark of memory, in bytes, associated with graphs since the last time it was reset. High watermark can only be reset to zero.
• GRAPH_MEM_ATTR_RESERVED_MEM_HIGH: High watermark of memory, in bytes, currently allocated for use by the CUDA graphs asynchronous allocator.

Parameters:

device - specifies the scope of the query

attr - attribute to get

value - pointer to value to set

ncuGraphClone

public static int ncuGraphClone(long phGraphClone,
 long originalGraph)

Unsafe version of: GraphClone

cuGraphClone

public static int cuGraphClone(PointerBuffer phGraphClone,
 long originalGraph)

Clones a graph.

This function creates a copy of originalGraph and returns it in phGraphClone. All parameters are copied into the cloned graph. The original graph may be modified after this call without affecting the clone.

Child graph nodes in the original graph are recursively copied into the clone.

Parameters:

phGraphClone - returns newly created cloned graph

originalGraph - graph to clone

ncuGraphNodeFindInClone

public static int ncuGraphNodeFindInClone(long phNode,
 long hOriginalNode,
 long hClonedGraph)

Unsafe version of: GraphNodeFindInClone

cuGraphNodeFindInClone

public static int cuGraphNodeFindInClone(PointerBuffer phNode,
 long hOriginalNode,
 long hClonedGraph)

Finds a cloned version of a node.

This function returns the node in hClonedGraph corresponding to hOriginalNode in the original graph.

hClonedGraph must have been cloned from hOriginalGraph via GraphClone. hOriginalNode must have been in hOriginalGraph at the time of the call to GraphClone, and the corresponding cloned node in hClonedGraph must not have been removed. The cloned node is then returned via phClonedNode.

Parameters:

phNode - returns handle to the cloned node

hOriginalNode - handle to the original node

hClonedGraph - cloned graph to query

ncuGraphNodeGetType

public static int ncuGraphNodeGetType(long hNode,
 long type)

Unsafe version of: GraphNodeGetType

cuGraphNodeGetType

public static int cuGraphNodeGetType(long hNode,
 IntBuffer type)

Returns a node's type.

Returns the node type of hNode in type.

Parameters:

hNode - node to query

type - pointer to return the node type

ncuGraphGetNodes

public static int ncuGraphGetNodes(long hGraph,
 long nodes,
 long numNodes)

Unsafe version of: GraphGetNodes

Parameters:

numNodes - see description

cuGraphGetNodes

public static int cuGraphGetNodes(long hGraph,
 @Nullable
 PointerBuffer nodes,
 PointerBuffer numNodes)

Returns a graph's nodes.

Returns a list of hGraph's nodes. nodes may be NULL, in which case this function will return the number of nodes in numNodes. Otherwise, numNodes entries will be filled in. If numNodes is higher than the actual number of nodes, the remaining entries in nodes will be set to NULL, and the number of nodes actually obtained will be returned in numNodes.

Parameters:

hGraph - graph to query

nodes - pointer to return the nodes

numNodes - see description

ncuGraphGetRootNodes

public static int ncuGraphGetRootNodes(long hGraph,
 long rootNodes,
 long numRootNodes)

Unsafe version of: GraphGetRootNodes

Parameters:

numRootNodes - see description

cuGraphGetRootNodes

public static int cuGraphGetRootNodes(long hGraph,
 @Nullable
 PointerBuffer rootNodes,
 PointerBuffer numRootNodes)

Returns a graph's root nodes.

Returns a list of hGraph's root nodes. rootNodes may be NULL, in which case this function will return the number of root nodes in numRootNodes. Otherwise, numRootNodes entries will be filled in. If numRootNodes is higher than the actual number of root nodes, the remaining entries in rootNodes will be set to NULL, and the number of nodes actually obtained will be returned in numRootNodes.

Parameters:

hGraph - graph to query

rootNodes - pointer to return the root nodes

numRootNodes - see description

ncuGraphGetEdges

public static int ncuGraphGetEdges(long hGraph,
 long from,
 long to,
 long numEdges)

Unsafe version of: GraphGetEdges

Parameters:

numEdges - see description

cuGraphGetEdges

public static int cuGraphGetEdges(long hGraph,
 @Nullable
 PointerBuffer from,
 @Nullable
 PointerBuffer to,
 PointerBuffer numEdges)

Returns a graph's dependency edges.

Returns a list of hGraph's dependency edges. Edges are returned via corresponding indices in from and to; that is, the node in to[i] has a dependency on the node in from[i]. from and to may both be NULL, in which case this function only returns the number of edges in numEdges. Otherwise, numEdges entries will be filled in. If numEdges is higher than the actual number of edges, the remaining entries in from and to will be set to NULL, and the number of edges actually returned will be written to numEdges.

Parameters:

hGraph - graph to get the edges from

from - location to return edge endpoints

to - location to return edge endpoints

numEdges - see description

ncuGraphNodeGetDependencies

public static int ncuGraphNodeGetDependencies(long hNode,
 long dependencies,
 long numDependencies)

Unsafe version of: GraphNodeGetDependencies

Parameters:

numDependencies - see description

cuGraphNodeGetDependencies

public static int cuGraphNodeGetDependencies(long hNode,
 @Nullable
 PointerBuffer dependencies,
 PointerBuffer numDependencies)

Returns a node's dependencies.

Returns a list of node's dependencies. dependencies may be NULL, in which case this function will return the number of dependencies in numDependencies. Otherwise, numDependencies entries will be filled in. If numDependencies is higher than the actual number of dependencies, the remaining entries in dependencies will be set to NULL, and the number of nodes actually obtained will be returned in numDependencies.

Parameters:

hNode - node to query

dependencies - pointer to return the dependencies

numDependencies - see description

ncuGraphNodeGetDependentNodes

public static int ncuGraphNodeGetDependentNodes(long hNode,
 long dependentNodes,
 long numDependentNodes)

Unsafe version of: GraphNodeGetDependentNodes

Parameters:

numDependentNodes - see description

cuGraphNodeGetDependentNodes

public static int cuGraphNodeGetDependentNodes(long hNode,
 @Nullable
 PointerBuffer dependentNodes,
 PointerBuffer numDependentNodes)

Returns a node's dependent nodes.

Returns a list of node's dependent nodes. dependentNodes may be NULL, in which case this function will return the number of dependent nodes in numDependentNodes. Otherwise, numDependentNodes entries will be filled in. If numDependentNodes is higher than the actual number of dependent nodes, the remaining entries in dependentNodes will be set to NULL, and the number of nodes actually obtained will be returned in numDependentNodes.

Parameters:

hNode - node to query

dependentNodes - pointer to return the dependent nodes

numDependentNodes - see description

ncuGraphAddDependencies

public static int ncuGraphAddDependencies(long hGraph,
 long from,
 long to,
 long numDependencies)

Unsafe version of: GraphAddDependencies

Parameters:

numDependencies - number of dependencies to be added

cuGraphAddDependencies

public static int cuGraphAddDependencies(long hGraph,
 @Nullable
 PointerBuffer from,
 @Nullable
 PointerBuffer to)

Adds dependency edges to a graph.

The number of dependencies to be added is defined by numDependencies Elements in from and to at corresponding indices define a dependency. Each node in from and to must belong to hGraph.

If numDependencies is 0, elements in from and to will be ignored. Specifying an existing dependency will return an error.

Parameters:

hGraph - graph to which dependencies are added

from - array of nodes that provide the dependencies

to - array of dependent nodes

ncuGraphRemoveDependencies

public static int ncuGraphRemoveDependencies(long hGraph,
 long from,
 long to,
 long numDependencies)

Unsafe version of: GraphRemoveDependencies

Parameters:

numDependencies - number of dependencies to be removed

cuGraphRemoveDependencies

public static int cuGraphRemoveDependencies(long hGraph,
 @Nullable
 PointerBuffer from,
 @Nullable
 PointerBuffer to)

Removes dependency edges from a graph.

The number of dependencies to be removed is defined by numDependencies. Elements in from and to at corresponding indices define a dependency. Each node in from and to must belong to hGraph.

If numDependencies is 0, elements in from and to will be ignored. Specifying a non-existing dependency will return an error.

Dependencies cannot be removed from graphs which contain allocation or free nodes. Any attempt to do so will return an error.

Parameters:

hGraph - graph from which to remove dependencies

from - array of nodes that provide the dependencies

to - array of dependent nodes

cuGraphDestroyNode

public static int cuGraphDestroyNode(long hNode)

Remove a node from the graph.

Removes hNode from its graph. This operation also severs any dependencies of other nodes on hNode and vice versa.

Nodes which belong to a graph which contains allocation or free nodes cannot be destroyed. Any attempt to do so will return an error.

Parameters:

hNode - node to remove

ncuGraphInstantiate

public static int ncuGraphInstantiate(long phGraphExec,
 long hGraph,
 long phErrorNode,
 long logBuffer,
 long bufferSize)

Unsafe version of: GraphInstantiate

Parameters:

bufferSize - size of the log buffer in bytes

cuGraphInstantiate

public static int cuGraphInstantiate(PointerBuffer phGraphExec,
 long hGraph,
 PointerBuffer phErrorNode,
 ByteBuffer logBuffer)

Creates an executable graph from a graph.

Instantiates hGraph as an executable graph. The graph is validated for any structural constraints or intra-node constraints which were not previously validated. If instantiation is successful, a handle to the instantiated graph is returned in phGraphExec.

If there are any errors, diagnostic information may be returned in errorNode and logBuffer. This is the primary way to inspect instantiation errors. The output will be null terminated unless the diagnostics overflow the buffer. In this case, they will be truncated, and the last byte can be inspected to determine if truncation occurred.

Parameters:

phGraphExec - returns instantiated graph

hGraph - graph to instantiate

phErrorNode - in case of an instantiation error, this may be modified to indicate a node contributing to the error

logBuffer - a character buffer to store diagnostic messages

ncuGraphInstantiateWithFlags

public static int ncuGraphInstantiateWithFlags(long phGraphExec,
 long hGraph,
 long flags)

Unsafe version of: GraphInstantiateWithFlags

cuGraphInstantiateWithFlags

public static int cuGraphInstantiateWithFlags(PointerBuffer phGraphExec,
 long hGraph,
 long flags)

Creates an executable graph from a graph.

Instantiates hGraph as an executable graph. The graph is validated for any structural constraints or intra-node constraints which were not previously validated. If instantiation is successful, a handle to the instantiated graph is returned in phGraphExec.

The flags parameter controls the behavior of instantiation and subsequent graph launches. Valid flags are:

• CUDA_GRAPH_INSTANTIATE_FLAG_AUTO_FREE_ON_LAUNCH, which configures a graph containing memory allocation nodes to automatically free any unfreed memory allocations before the graph is relaunched.

If hGraph contains any allocation or free nodes, there can be at most one executable graph in existence for that graph at a time.

An attempt to instantiate a second executable graph before destroying the first with GraphExecDestroy will result in an error.

Parameters:

phGraphExec - returns instantiated graph

hGraph - graph to instantiate

flags - flags to control instantiation. See CUgraphInstantiate_flags.

ncuGraphExecKernelNodeSetParams

public static int ncuGraphExecKernelNodeSetParams(long hGraphExec,
 long hNode,
 long nodeParams)

Unsafe version of: GraphExecKernelNodeSetParams

cuGraphExecKernelNodeSetParams

public static int cuGraphExecKernelNodeSetParams(long hGraphExec,
 long hNode,
 CUDA_KERNEL_NODE_PARAMS nodeParams)

Sets the parameters for a kernel node in the given graphExec.

Sets the parameters of a kernel node in an executable graph hGraphExec. The node is identified by the corresponding node hNode in the non-executable graph, from which the executable graph was instantiated.

hNode must not have been removed from the original graph. The func field of nodeParams cannot be modified and must match the original value. All other values can be modified.

The modifications take effect at the next launch of hGraphExec. Already enqueued or running launches of hGraphExec are not affected by this call. hNode is also not modified by this call.

Parameters:

hGraphExec - the executable graph in which to set the specified node

hNode - kernel node from the graph from which graphExec was instantiated

nodeParams - updated parameters to set

ncuGraphExecMemcpyNodeSetParams

public static int ncuGraphExecMemcpyNodeSetParams(long hGraphExec,
 long hNode,
 long copyParams,
 long ctx)

Unsafe version of: GraphExecMemcpyNodeSetParams

cuGraphExecMemcpyNodeSetParams

public static int cuGraphExecMemcpyNodeSetParams(long hGraphExec,
 long hNode,
 CUDA_MEMCPY3D copyParams,
 long ctx)

Sets the parameters for a memcpy node in the given graphExec.

Updates the work represented by hNode in hGraphExec as though hNode had contained copyParams at instantiation. hNode must remain in the graph which was used to instantiate hGraphExec. Changed edges to and from hNode are ignored.

The source and destination memory in copyParams must be allocated from the same contexts as the original source and destination memory. Both the instantiation-time memory operands and the memory operands in copyParams must be 1-dimensional. Zero-length operations are not supported.

The modifications only affect future launches of hGraphExec. Already enqueued or running launches of hGraphExec are not affected by this call. hNode is also not modified by this call.

Returns CUDA_ERROR_INVALID_VALUE if the memory operands' mappings changed or either the original or new memory operands are multidimensional.

Parameters:

hGraphExec - the executable graph in which to set the specified node

hNode - memcpy node from the graph which was used to instantiate graphExec

copyParams - the updated parameters to set

ctx - context on which to run the node

ncuGraphExecMemsetNodeSetParams

public static int ncuGraphExecMemsetNodeSetParams(long hGraphExec,
 long hNode,
 long memsetParams,
 long ctx)

Unsafe version of: GraphExecMemsetNodeSetParams

cuGraphExecMemsetNodeSetParams

public static int cuGraphExecMemsetNodeSetParams(long hGraphExec,
 long hNode,
 CUDA_MEMSET_NODE_PARAMS memsetParams,
 long ctx)

Sets the parameters for a memset node in the given graphExec.

Updates the work represented by hNode in hGraphExec as though hNode had contained memsetParams at instantiation. hNode must remain in the graph which was used to instantiate hGraphExec. Changed edges to and from hNode are ignored.

The destination memory in memsetParams must be allocated from the same contexts as the original destination memory. Both the instantiation-time memory operand and the memory operand in memsetParams must be 1-dimensional. Zero-length operations are not supported.

The modifications only affect future launches of hGraphExec. Already enqueued or running launches of hGraphExec are not affected by this call. hNode is also not modified by this call.

Returns CUDA_ERROR_INVALID_VALUE if the memory operand's mappings changed or either the original or new memory operand are multidimensional.

Parameters:

hGraphExec - the executable graph in which to set the specified node

hNode - memset node from the graph which was used to instantiate graphExec

memsetParams - the updated parameters to set

ctx - context on which to run the node

ncuGraphExecHostNodeSetParams

public static int ncuGraphExecHostNodeSetParams(long hGraphExec,
 long hNode,
 long nodeParams)

Unsafe version of: GraphExecHostNodeSetParams

cuGraphExecHostNodeSetParams

public static int cuGraphExecHostNodeSetParams(long hGraphExec,
 long hNode,
 CUDA_HOST_NODE_PARAMS nodeParams)

Sets the parameters for a host node in the given graphExec.

Updates the work represented by hNode in hGraphExec as though hNode had contained nodeParams at instantiation. hNode must remain in the graph which was used to instantiate hGraphExec. Changed edges to and from hNode are ignored.

The modifications only affect future launches of hGraphExec. Already enqueued or running launches of hGraphExec are not affected by this call. hNode is also not modified by this call.

Parameters:

hGraphExec - the executable graph in which to set the specified node

hNode - host node from the graph which was used to instantiate graphExec

nodeParams - the updated parameters to set

cuGraphExecChildGraphNodeSetParams

public static int cuGraphExecChildGraphNodeSetParams(long hGraphExec,
 long hNode,
 long childGraph)

Updates node parameters in the child graph node in the given graphExec.

Updates the work represented by hNode in hGraphExec as though the nodes contained in hNode's graph had the parameters contained in childGraph's nodes at instantiation. hNode must remain in the graph which was used to instantiate hGraphExec. Changed edges to and from hNode are ignored.

The modifications only affect future launches of hGraphExec. Already enqueued or running launches of hGraphExec are not affected by this call. hNode is also not modified by this call.

The topology of childGraph, as well as the node insertion order, must match that of the graph contained in hNode. See GraphExecUpdate for a list of restrictions on what can be updated in an instantiated graph. The update is recursive, so child graph nodes contained within the top level child graph will also be updated.

Parameters:

hGraphExec - the executable graph in which to set the specified node

hNode - host node from the graph which was used to instantiate graphExec

childGraph - the graph supplying the updated parameters

cuGraphExecEventRecordNodeSetEvent

public static int cuGraphExecEventRecordNodeSetEvent(long hGraphExec,
 long hNode,
 long event)

Sets the event for an event record node in the given graphExec.

Sets the event of an event record node in an executable graph hGraphExec. The node is identified by the corresponding node hNode in the non-executable graph, from which the executable graph was instantiated.

The modifications only affect future launches of hGraphExec. Already enqueued or running launches of hGraphExec are not affected by this call. hNode is also not modified by this call.

Parameters:

hGraphExec - the executable graph in which to set the specified node

hNode - event record node from the graph from which graphExec was instantiated

event - updated event to use

cuGraphExecEventWaitNodeSetEvent

public static int cuGraphExecEventWaitNodeSetEvent(long hGraphExec,
 long hNode,
 long event)

Sets the event for an event wait node in the given graphExec.

Sets the event of an event wait node in an executable graph hGraphExec. The node is identified by the corresponding node hNode in the non-executable graph, from which the executable graph was instantiated.

The modifications only affect future launches of hGraphExec. Already enqueued or running launches of hGraphExec are not affected by this call. hNode is also not modified by this call.

Parameters:

hGraphExec - the executable graph in which to set the specified node

hNode - event wait node from the graph from which graphExec was instantiated

event - updated event to use

ncuGraphExecExternalSemaphoresSignalNodeSetParams

public static int ncuGraphExecExternalSemaphoresSignalNodeSetParams(long hGraphExec,
 long hNode,
 long nodeParams)

Unsafe version of: GraphExecExternalSemaphoresSignalNodeSetParams

cuGraphExecExternalSemaphoresSignalNodeSetParams

public static int cuGraphExecExternalSemaphoresSignalNodeSetParams(long hGraphExec,
 long hNode,
 CUDA_EXT_SEM_SIGNAL_NODE_PARAMS nodeParams)

Sets the parameters for an external semaphore signal node in the given graphExec.

Sets the parameters of an external semaphore signal node in an executable graph hGraphExec. The node is identified by the corresponding node hNode in the non-executable graph, from which the executable graph was instantiated.

hNode must not have been removed from the original graph.

The modifications only affect future launches of hGraphExec. Already enqueued or running launches of hGraphExec are not affected by this call. hNode is also not modified by this call.

Changing nodeParams->numExtSems is not supported.

Parameters:

hGraphExec - the executable graph in which to set the specified node

hNode - semaphore signal node from the graph from which graphExec was instantiated

nodeParams - updated Parameters to set

ncuGraphExecExternalSemaphoresWaitNodeSetParams

public static int ncuGraphExecExternalSemaphoresWaitNodeSetParams(long hGraphExec,
 long hNode,
 long nodeParams)

Unsafe version of: GraphExecExternalSemaphoresWaitNodeSetParams

cuGraphExecExternalSemaphoresWaitNodeSetParams

public static int cuGraphExecExternalSemaphoresWaitNodeSetParams(long hGraphExec,
 long hNode,
 CUDA_EXT_SEM_WAIT_NODE_PARAMS nodeParams)

Sets the parameters for an external semaphore wait node in the given graphExec.

Sets the parameters of an external semaphore wait node in an executable graph hGraphExec. The node is identified by the corresponding node hNode in the non-executable graph, from which the executable graph was instantiated.

hNode must not have been removed from the original graph.

The modifications only affect future launches of hGraphExec. Already enqueued or running launches of hGraphExec are not affected by this call. hNode is also not modified by this call.

Changing nodeParams->numExtSems is not supported.

Parameters:

hGraphExec - the executable graph in which to set the specified node

hNode - semaphore wait node from the graph from which graphExec was instantiated

nodeParams - updated Parameters to set

cuGraphUpload

public static int cuGraphUpload(long hGraphExec,
 long hStream)

Uploads an executable graph in a stream.

Uploads hGraphExec to the device in hStream without executing it. Uploads of the same hGraphExec will be serialized. Each upload is ordered behind both any previous work in hStream and any previous launches of hGraphExec. Uses memory cached by stream to back the allocations owned by hGraphExec.

Parameters:

hGraphExec - executable graph to upload

hStream - stream in which to upload the graph

cuGraphLaunch

public static int cuGraphLaunch(long hGraphExec,
 long hStream)

Launches an executable graph in a stream.

Executes hGraphExec in hStream. Only one instance of hGraphExec may be executing at a time. Each launch is ordered behind both any previous work in hStream and any previous launches of hGraphExec. To execute a graph concurrently, it must be instantiated multiple times into multiple executable graphs.

If any allocations created by hGraphExec remain unfreed (from a previous launch) and hGraphExec was not instantiated with CUDA_GRAPH_INSTANTIATE_FLAG_AUTO_FREE_ON_LAUNCH, the launch will fail with CUDA_ERROR_INVALID_VALUE.

Parameters:

hGraphExec - executable graph to launch

hStream - stream in which to launch the graph

cuGraphExecDestroy

public static int cuGraphExecDestroy(long hGraphExec)

Destroys an executable graph.

Destroys the executable graph specified by hGraphExec, as well as all of its executable nodes. If the executable graph is in-flight, it will not be terminated, but rather freed asynchronously on completion.

Parameters:

hGraphExec - executable graph to destroy

cuGraphDestroy

public static int cuGraphDestroy(long hGraph)

Destroys a graph.

Destroys the graph specified by hGraph, as well as all of its nodes.

Parameters:

hGraph - graph to destroy

ncuGraphExecUpdate

public static int ncuGraphExecUpdate(long hGraphExec,
 long hGraph,
 long hErrorNode_out,
 long updateResult_out)

Unsafe version of: GraphExecUpdate

cuGraphExecUpdate

public static int cuGraphExecUpdate(long hGraphExec,
 long hGraph,
 PointerBuffer hErrorNode_out,
 IntBuffer updateResult_out)

Check whether an executable graph can be updated with a graph and perform the update if possible.

Updates the node parameters in the instantiated graph specified by hGraphExec with the node parameters in a topologically identical graph specified by hGraph.

Limitations:

• Kernel nodes:
  • The owning context of the function cannot change.
  • A node whose function originally did not use CUDA dynamic parallelism cannot be updated to a function which uses CDP
• Memset and memcpy nodes:
  • The CUDA device(s) to which the operand(s) was allocated/mapped cannot change.
  • The source/destination memory must be allocated from the same contexts as the original source/destination memory.
  • Only 1D memsets can be changed.
• Additional memcpy node restrictions:
  • Changing either the source or destination memory type(i.e. CU_MEMORYTYPE_DEVICE, CU_MEMORYTYPE_ARRAY, etc.) is not supported.
• External semaphore wait nodes and record nodes:
  • Changing either the source or destination memory type(i.e. CU_MEMORYTYPE_DEVICE, CU_MEMORYTYPE_ARRAY, etc.) is not supported.

Note: The API may add further restrictions in future releases. The return code should always be checked.

cuGraphExecUpdate sets updateResult_out to GRAPH_EXEC_UPDATE_ERROR_TOPOLOGY_CHANGED under the following conditions:

• The count of nodes directly in hGraphExec and hGraph differ, in which case hErrorNode_out is NULL.
• A node is deleted in hGraph but not not its pair from hGraphExec, in which case hErrorNode_out is NULL.
• A node is deleted in hGraphExec but not its pair from hGraph, in which case hErrorNode_out is the pairless node from hGraph.
• The dependent nodes of a pair differ, in which case hErrorNode_out is the node from hGraph.

cuGraphExecUpdate sets updateResult_out to:

• GRAPH_EXEC_UPDATE_ERROR if passed an invalid value.
• GRAPH_EXEC_UPDATE_ERROR_TOPOLOGY_CHANGED if the graph topology changed
• GRAPH_EXEC_UPDATE_ERROR_NODE_TYPE_CHANGED if the type of a node changed, in which case hErrorNode_out is set to the node from hGraph.
• GRAPH_EXEC_UPDATE_ERROR_UNSUPPORTED_FUNCTION_CHANGE if the function changed in an unsupported way(see note above), in which case hErrorNode_out is set to the node from hGraph
• GRAPH_EXEC_UPDATE_ERROR_PARAMETERS_CHANGED if any parameters to a node changed in a way that is not supported, in which case hErrorNode_out is set to the node from hGraph.
• GRAPH_EXEC_UPDATE_ERROR_NOT_SUPPORTED if something about a node is unsupported, like the node's type or configuration, in which case hErrorNode_out is set to the node from hGraph

If updateResult_out isn't set in one of the situations described above, the update check passes and cuGraphExecUpdate updates hGraphExec to match the contents of hGraph. If an error happens during the update, updateResult_out will be set to GRAPH_EXEC_UPDATE_ERROR; otherwise, updateResult_out is set to GRAPH_EXEC_UPDATE_SUCCESS.

cuGraphExecUpdate returns CUDA_SUCCESS when the updated was performed successfully. It returns CUDA_ERROR_GRAPH_EXEC_UPDATE_FAILURE if the graph update was not performed because it included changes which violated constraints specific to instantiated graph update.

Parameters:

hGraphExec - the instantiated graph to be updated

hGraph - the graph containing the updated parameters

hErrorNode_out - the node which caused the permissibility check to forbid the update, if any

updateResult_out - whether the graph update was permitted. If was forbidden, the reason why.

cuGraphKernelNodeCopyAttributes

public static int cuGraphKernelNodeCopyAttributes(long dst,
 long src)

Copies attributes from source node to destination node.

Copies attributes from source node src to destination node dst. Both node must have the same context.

Parameters:

dst - destination node

src - source node. For list of attributes see CUkernelNodeAttrID.

ncuGraphKernelNodeGetAttribute

public static int ncuGraphKernelNodeGetAttribute(long hNode,
 int attr,
 long value_out)

Unsafe version of: GraphKernelNodeGetAttribute

cuGraphKernelNodeGetAttribute

public static int cuGraphKernelNodeGetAttribute(long hNode,
 int attr,
 CUkernelNodeAttrValue value_out)

Queries node attribute.

Queries attribute attr from node hNode and stores it in corresponding member of value_out.

ncuGraphKernelNodeSetAttribute

public static int ncuGraphKernelNodeSetAttribute(long hNode,
 int attr,
 long value)

Unsafe version of: GraphKernelNodeSetAttribute

cuGraphKernelNodeSetAttribute

public static int cuGraphKernelNodeSetAttribute(long hNode,
 int attr,
 CUkernelNodeAttrValue value)

Sets node attribute.

Sets attribute attr on node hNode from corresponding attribute of value.

ncuGraphDebugDotPrint

public static int ncuGraphDebugDotPrint(long hGraph,
 long path,
 int flags)

Unsafe version of: GraphDebugDotPrint

cuGraphDebugDotPrint

public static int cuGraphDebugDotPrint(long hGraph,
 ByteBuffer path,
 int flags)

Write a DOT file describing graph structure.

Using the provided hGraph, write to path a DOT formatted description of the graph. By default this includes the graph topology, node types, node id, kernel names and memcpy direction. flags can be specified to write more detailed information about each node type such as parameter values, kernel attributes, node and function handles.

Parameters:

hGraph - the graph to create a DOT file from

path - the path to write the DOT file to

flags - flags from CUgraphDebugDot_flags for specifying which additional node information to write

cuGraphDebugDotPrint

public static int cuGraphDebugDotPrint(long hGraph,
 CharSequence path,
 int flags)

Write a DOT file describing graph structure.

Using the provided hGraph, write to path a DOT formatted description of the graph. By default this includes the graph topology, node types, node id, kernel names and memcpy direction. flags can be specified to write more detailed information about each node type such as parameter values, kernel attributes, node and function handles.

Parameters:

hGraph - the graph to create a DOT file from

path - the path to write the DOT file to

flags - flags from CUgraphDebugDot_flags for specifying which additional node information to write

ncuUserObjectCreate

public static int ncuUserObjectCreate(long object_out,
 long ptr,
 long destroy,
 int initialRefcount,
 int flags)

Unsafe version of: UserObjectCreate

cuUserObjectCreate

public static int cuUserObjectCreate(PointerBuffer object_out,
 long ptr,
 CUhostFnI destroy,
 int initialRefcount,
 int flags)

Create a user object.

Create a user object with the specified destructor callback and initial reference count. The initial references are owned by the caller.

Destructor callbacks cannot make CUDA API calls and should avoid blocking behavior, as they are executed by a shared internal thread. Another thread may be signaled to perform such actions, if it does not block forward progress of tasks scheduled through CUDA.

See CUDA User Objects in the CUDA C++ Programming Guide for more information on user objects.

Parameters:

object_out - location to return the user object handle

ptr - the pointer to pass to the destroy function

destroy - callback to free the user object when it is no longer in use

initialRefcount - the initial refcount to create the object with, typically 1. The initial references are owned by the calling thread.

flags - currently it is required to pass USER_OBJECT_NO_DESTRUCTOR_SYNC, which is the only defined flag. This indicates that the destroy callback cannot be waited on by any CUDA API. Users requiring synchronization of the callback should signal its completion manually.

cuUserObjectRetain

public static int cuUserObjectRetain(long object,
 int count)

Retain a reference to a user object.

Retains new references to a user object. The new references are owned by the caller.

See CUDA User Objects in the CUDA C++ Programming Guide for more information on user objects.

Parameters:

object - the object to retain

count - the number of references to retain, typically 1. Must be nonzero and not larger than INT_MAX.

cuUserObjectRelease

public static int cuUserObjectRelease(long object,
 int count)

Release a reference to a user object.

Releases user object references owned by the caller. The object's destructor is invoked if the reference count reaches zero.

It is undefined behavior to release references not owned by the caller, or to use a user object handle after all references are released.

See CUDA User Objects in the CUDA C++ Programming Guide for more information on user objects.

Parameters:

object - the object to release

count - the number of references to release, typically 1. Must be nonzero and not larger than INT_MAX.

cuGraphRetainUserObject

public static int cuGraphRetainUserObject(long graph,
 long object,
 int count,
 int flags)

Retain a reference to a user object from a graph.

Creates or moves user object references that will be owned by a CUDA graph.

See CUDA User Objects in the CUDA C++ Programming Guide for more information on user objects.

Parameters:

graph - the graph to associate the reference with

object - the user object to retain a reference for

count - the number of references to add to the graph, typically 1. Must be nonzero and not larger than INT_MAX.

flags - the optional flag GRAPH_USER_OBJECT_MOVE transfers references from the calling thread, rather than create new references. Pass 0 to create new references.

cuGraphReleaseUserObject

public static int cuGraphReleaseUserObject(long graph,
 long object,
 int count)

Release a user object reference from a graph.

Releases user object references owned by a graph.

See CUDA User Objects in the CUDA C++ Programming Guide for more information on user objects.

Parameters:

graph - the graph that will release the reference

object - the user object to release a reference for

count - the number of references to release, typically 1. Must be nonzero and not larger than INT_MAX.

ncuOccupancyMaxActiveBlocksPerMultiprocessor

public static int ncuOccupancyMaxActiveBlocksPerMultiprocessor(long numBlocks,
 long func,
 int blockSize,
 long dynamicSMemSize)

Unsafe version of: OccupancyMaxActiveBlocksPerMultiprocessor

cuOccupancyMaxActiveBlocksPerMultiprocessor

public static int cuOccupancyMaxActiveBlocksPerMultiprocessor(IntBuffer numBlocks,
 long func,
 int blockSize,
 long dynamicSMemSize)

Returns occupancy of a function.

Returns in *numBlocks the number of the maximum active blocks per streaming multiprocessor.

Parameters:

numBlocks - returned occupancy

func - kernel for which occupancy is calculated

blockSize - block size the kernel is intended to be launched with

dynamicSMemSize - per-block dynamic shared memory usage intended, in bytes

ncuOccupancyMaxActiveBlocksPerMultiprocessorWithFlags

public static int ncuOccupancyMaxActiveBlocksPerMultiprocessorWithFlags(long numBlocks,
 long func,
 int blockSize,
 long dynamicSMemSize,
 int flags)

Unsafe version of: OccupancyMaxActiveBlocksPerMultiprocessorWithFlags

cuOccupancyMaxActiveBlocksPerMultiprocessorWithFlags

public static int cuOccupancyMaxActiveBlocksPerMultiprocessorWithFlags(IntBuffer numBlocks,
 long func,
 int blockSize,
 long dynamicSMemSize,
 int flags)

Returns occupancy of a function.

Returns in *numBlocks the number of the maximum active blocks per streaming multiprocessor.

The Flags parameter controls how special cases are handled. The valid flags are:

• OCCUPANCY_DEFAULT, which maintains the default behavior as OccupancyMaxActiveBlocksPerMultiprocessor;
• OCCUPANCY_DISABLE_CACHING_OVERRIDE, which suppresses the default behavior on platform where global caching affects occupancy. On such platforms, if caching is enabled, but per-block SM resource usage would result in zero occupancy, the occupancy calculator will calculate the occupancy as if caching is disabled. Setting OCCUPANCY_DISABLE_CACHING_OVERRIDE makes the occupancy calculator to return 0 in such cases. More information can be found about this feature in the "Unified L1/Texture Cache" section of the Maxwell tuning guide.

Parameters:

numBlocks - returned occupancy

func - kernel for which occupancy is calculated

blockSize - block size the kernel is intended to be launched with

dynamicSMemSize - per-block dynamic shared memory usage intended, in bytes

flags - requested behavior for the occupancy calculator

ncuOccupancyMaxPotentialBlockSize

public static int ncuOccupancyMaxPotentialBlockSize(long minGridSize,
 long blockSize,
 long func,
 long blockSizeToDynamicSMemSize,
 long dynamicSMemSize,
 int blockSizeLimit)

Unsafe version of: OccupancyMaxPotentialBlockSize

cuOccupancyMaxPotentialBlockSize

public static int cuOccupancyMaxPotentialBlockSize(IntBuffer minGridSize,
 IntBuffer blockSize,
 long func,
 @Nullable
 CUoccupancyB2DSizeI blockSizeToDynamicSMemSize,
 long dynamicSMemSize,
 int blockSizeLimit)

Suggest a launch configuration with reasonable occupancy.

Returns in *blockSize a reasonable block size that can achieve the maximum occupancy (or, the maximum number of active warps with the fewest blocks per multiprocessor), and in *minGridSize the minimum grid size to achieve the maximum occupancy.

If blockSizeLimit is 0, the configurator will use the maximum block size permitted by the device / function instead.

If per-block dynamic shared memory allocation is not needed, the user should leave both blockSizeToDynamicSMemSize and dynamicSMemSize as 0.

If per-block dynamic shared memory allocation is needed, then if the dynamic shared memory size is constant regardless of block size, the size should be passed through dynamicSMemSize, and blockSizeToDynamicSMemSize should be NULL.

Otherwise, if the per-block dynamic shared memory size varies with different block sizes, the user needs to provide a unary function through blockSizeToDynamicSMemSize that computes the dynamic shared memory needed by func for any given block size. dynamicSMemSize is ignored. An example signature is:

 // Take block size, returns dynamic shared memory needed
 size_t blockToSmem(int blockSize);

Parameters:

minGridSize - returned minimum grid size needed to achieve the maximum occupancy

blockSize - returned maximum block size that can achieve the maximum occupancy

func - kernel for which launch configuration is calculated

blockSizeToDynamicSMemSize - a function that calculates how much per-block dynamic shared memory func uses based on the block size

dynamicSMemSize - dynamic shared memory usage intended, in bytes

blockSizeLimit - the maximum block size func is designed to handle

ncuOccupancyMaxPotentialBlockSizeWithFlags

public static int ncuOccupancyMaxPotentialBlockSizeWithFlags(long minGridSize,
 long blockSize,
 long func,
 long blockSizeToDynamicSMemSize,
 long dynamicSMemSize,
 int blockSizeLimit,
 int flags)

Unsafe version of: OccupancyMaxPotentialBlockSizeWithFlags

cuOccupancyMaxPotentialBlockSizeWithFlags

public static int cuOccupancyMaxPotentialBlockSizeWithFlags(IntBuffer minGridSize,
 IntBuffer blockSize,
 long func,
 @Nullable
 CUoccupancyB2DSizeI blockSizeToDynamicSMemSize,
 long dynamicSMemSize,
 int blockSizeLimit,
 int flags)

Suggest a launch configuration with reasonable occupancy.

An extended version of OccupancyMaxPotentialBlockSize. In addition to arguments passed to OccupancyMaxPotentialBlockSize, OccupancyMaxPotentialBlockSizeWithFlags also takes a Flags parameter.

The Flags parameter controls how special cases are handled. The valid flags are:

• OCCUPANCY_DEFAULT, which maintains the default behavior as OccupancyMaxPotentialBlockSize;
• OCCUPANCY_DISABLE_CACHING_OVERRIDE, which suppresses the default behavior on platform where global caching affects occupancy. On such platforms, the launch configurations that produces maximal occupancy might not support global caching. Setting OCCUPANCY_DISABLE_CACHING_OVERRIDE guarantees that the the produced launch configuration is global caching compatible at a potential cost of occupancy. More information can be found about this feature in the "Unified L1/Texture Cache" section of the Maxwell tuning guide.

Parameters:

minGridSize - returned minimum grid size needed to achieve the maximum occupancy

blockSize - returned maximum block size that can achieve the maximum occupancy

func - kernel for which launch configuration is calculated

blockSizeToDynamicSMemSize - a function that calculates how much per-block dynamic shared memory func uses based on the block size

dynamicSMemSize - dynamic shared memory usage intended, in bytes

blockSizeLimit - the maximum block size func is designed to handle

flags - options

ncuOccupancyAvailableDynamicSMemPerBlock

public static int ncuOccupancyAvailableDynamicSMemPerBlock(long dynamicSmemSize,
 long func,
 int numBlocks,
 int blockSize)

Unsafe version of: OccupancyAvailableDynamicSMemPerBlock

cuOccupancyAvailableDynamicSMemPerBlock

public static int cuOccupancyAvailableDynamicSMemPerBlock(PointerBuffer dynamicSmemSize,
 long func,
 int numBlocks,
 int blockSize)

Returns dynamic shared memory available per block when launching numBlocks blocks on SM.

Returns in *dynamicSmemSize the maximum size of dynamic shared memory to allow numBlocks blocks per SM.

Parameters:

dynamicSmemSize - returned maximum dynamic shared memory

func - kernel function for which occupancy is calculated

numBlocks - number of blocks to fit on SM

blockSize - size of the blocks

cuTexRefSetArray

public static int cuTexRefSetArray(long hTexRef,
 long hArray,
 int Flags)

Binds an array as a texture reference. (Deprecated)

Binds the CUDA array hArray to the texture reference hTexRef. Any previous address or CUDA array state associated with the texture reference is superseded by this function. Flags must be set to TRSA_OVERRIDE_FORMAT. Any CUDA array previously bound to hTexRef is unbound.

Parameters:

hTexRef - texture reference to bind

hArray - array to bind

Flags - options (must be TRSA_OVERRIDE_FORMAT)

cuTexRefSetMipmappedArray

public static int cuTexRefSetMipmappedArray(long hTexRef,
 long hMipmappedArray,
 int Flags)

Binds a mipmapped array to a texture reference. (Deprecated)

Binds the CUDA mipmapped array hMipmappedArray to the texture reference hTexRef. Any previous address or CUDA array state associated with the texture reference is superseded by this function. Flags must be set to TRSA_OVERRIDE_FORMAT. Any CUDA array previously bound to hTexRef is unbound.

Parameters:

hTexRef - texture reference to bind

hMipmappedArray - mipmapped array to bind

Flags - options (must be TRSA_OVERRIDE_FORMAT)

ncuTexRefSetAddress

public static int ncuTexRefSetAddress(long ByteOffset,
 long hTexRef,
 long dptr,
 long bytes)

Unsafe version of: TexRefSetAddress

cuTexRefSetAddress

public static int cuTexRefSetAddress(PointerBuffer ByteOffset,
 long hTexRef,
 long dptr,
 long bytes)

Binds an address as a texture reference. (Deprecated)

Binds a linear address range to the texture reference hTexRef. Any previous address or CUDA array state associated with the texture reference is superseded by this function. Any memory previously bound to hTexRef is unbound.

Since the hardware enforces an alignment requirement on texture base addresses, TexRefSetAddress passes back a byte offset in *ByteOffset that must be applied to texture fetches in order to read from the desired memory. This offset must be divided by the texel size and passed to kernels that read from the texture so they can be applied to the tex1Dfetch() function.

If the device memory pointer was returned from MemAlloc, the offset is guaranteed to be 0 and NULL may be passed as the ByteOffset parameter.

The total number of elements (or texels) in the linear address range cannot exceed DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH. The number of elements is computed as (bytes / bytesPerElement), where bytesPerElement is determined from the data format and number of components set using TexRefSetFormat.

Parameters:

ByteOffset - returned byte offset

hTexRef - texture reference to bind

dptr - device pointer to bind

bytes - size of memory to bind in bytes

ncuTexRefSetAddress2D

public static int ncuTexRefSetAddress2D(long hTexRef,
 long desc,
 long dptr,
 long Pitch)

Unsafe version of: TexRefSetAddress2D

cuTexRefSetAddress2D

public static int cuTexRefSetAddress2D(long hTexRef,
 CUDA_ARRAY_DESCRIPTOR desc,
 long dptr,
 long Pitch)

Binds an address as a 2D texture reference. (Deprecated)

Binds a linear address range to the texture reference hTexRef. Any previous address or CUDA array state associated with the texture reference is superseded by this function. Any memory previously bound to hTexRef is unbound.

Using a tex2D() function inside a kernel requires a call to either TexRefSetArray to bind the corresponding texture reference to an array, or TexRefSetAddress2D to bind the texture reference to linear memory.

Function calls to TexRefSetFormat cannot follow calls to TexRefSetAddress2D for the same texture reference.

It is required that dptr be aligned to the appropriate hardware-specific texture alignment. You can query this value using the device attribute DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT. If an unaligned dptr is supplied, CUDA_ERROR_INVALID_VALUE is returned.

Pitch has to be aligned to the hardware-specific texture pitch alignment. This value can be queried using the device attribute DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT. If an unaligned Pitch is supplied, CUDA_ERROR_INVALID_VALUE is returned.

Width and Height, which are specified in elements (or texels), cannot exceed DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH and DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT respectively. Pitch, which is specified in bytes, cannot exceed DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH.

Parameters:

hTexRef - texture reference to bind

desc - descriptor of CUDA array

dptr - device pointer to bind

Pitch - line pitch in bytes

cuTexRefSetFormat

public static int cuTexRefSetFormat(long hTexRef,
 int fmt,
 int NumPackedComponents)

Sets the format for a texture reference. (Deprecated)

Specifies the format of the data to be read by the texture reference hTexRef. fmt and NumPackedComponents are exactly analogous to the Format and NumChannels members of the CUDA_ARRAY_DESCRIPTOR structure: They specify the format of each component and the number of components per array element.

Parameters:

hTexRef - texture reference

fmt - format to set

NumPackedComponents - number of components per array element

cuTexRefSetAddressMode

public static int cuTexRefSetAddressMode(long hTexRef,
 int dim,
 int am)

Sets the addressing mode for a texture reference. (Deprecated)

Specifies the addressing mode am for the given dimension dim of the texture reference hTexRef. If dim is zero, the addressing mode is applied to the first parameter of the functions used to fetch from the texture; if dim is 1, the second, and so on.

Note that this call has no effect if hTexRef is bound to linear memory. Also, if the flag, TRSF_NORMALIZED_COORDINATES, is not set, the only supported address mode is TR_ADDRESS_MODE_CLAMP.

Parameters:

hTexRef - texture reference

dim - dimension

am - addressing mode to set

cuTexRefSetFilterMode

public static int cuTexRefSetFilterMode(long hTexRef,
 int fm)

Sets the filtering mode for a texture reference. (Deprecated)

Specifies the filtering mode fm to be used when reading memory through the texture reference hTexRef.

Note that this call has no effect if hTexRef is bound to linear memory.

Parameters:

hTexRef - texture reference

fm - filtering mode to set

cuTexRefSetMipmapFilterMode

public static int cuTexRefSetMipmapFilterMode(long hTexRef,
 int fm)

Sets the mipmap filtering mode for a texture reference (Deprecated)

Specifies the mipmap filtering mode fm to be used when reading memory through the texture reference hTexRef.

Note that this call has no effect if hTexRef is not bound to a mipmapped array.

Parameters:

hTexRef - texture reference

fm - filtering mode to set

cuTexRefSetMipmapLevelBias

public static int cuTexRefSetMipmapLevelBias(long hTexRef,
 float bias)

Sets the mipmap level bias for a texture reference. (Deprecated)

Specifies the mipmap level bias bias to be added to the specified mipmap level when reading memory through the texture reference hTexRef.

Note that this call has no effect if hTexRef is not bound to a mipmapped array.

Parameters:

hTexRef - texture reference

bias - mipmap level bias

cuTexRefSetMipmapLevelClamp

public static int cuTexRefSetMipmapLevelClamp(long hTexRef,
 float minMipmapLevelClamp,
 float maxMipmapLevelClamp)

Sets the mipmap min/max mipmap level clamps for a texture reference. (Deprecated)

Specifies the min/max mipmap level clamps, minMipmapLevelClamp and maxMipmapLevelClamp respectively, to be used when reading memory through the texture reference hTexRef.

Note that this call has no effect if hTexRef is not bound to a mipmapped array.

Parameters:

hTexRef - texture reference

minMipmapLevelClamp - mipmap min level clamp

maxMipmapLevelClamp - mipmap max level clamp

cuTexRefSetMaxAnisotropy

public static int cuTexRefSetMaxAnisotropy(long hTexRef,
 int maxAniso)

Sets the maximum anisotropy for a texture reference. (Deprecated)

Specifies the maximum anisotropy maxAniso to be used when reading memory through the texture reference hTexRef.

Note that this call has no effect if hTexRef is bound to linear memory.

Parameters:

hTexRef - texture reference

maxAniso - maximum anisotropy

ncuTexRefSetBorderColor

public static int ncuTexRefSetBorderColor(long hTexRef,
 long pBorderColor)

Unsafe version of: TexRefSetBorderColor

cuTexRefSetBorderColor

public static int cuTexRefSetBorderColor(long hTexRef,
 FloatBuffer pBorderColor)

Sets the border color for a texture reference. (Deprecated)

Specifies the value of the RGBA color via the pBorderColor to the texture reference hTexRef. The color value supports only float type and holds color components in the following sequence: pBorderColor[0] holds 'R' component pBorderColor[1] holds 'G' component pBorderColor[2] holds 'B' component pBorderColor[3] holds 'A' component.

Note that the color values can be set only when the Address mode is set to TR_ADDRESS_MODE_BORDER using TexRefSetAddressMode. Applications using integer border color values have to "reinterpret_cast" their values to float.

Parameters:

hTexRef - texture reference

pBorderColor - RGBA color

cuTexRefSetFlags

public static int cuTexRefSetFlags(long hTexRef,
 int Flags)

Sets the flags for a texture reference. (Deprecated)

Specifies optional flags via Flags to specify the behavior of data returned through the texture reference hTexRef. The valid flags are:

• TRSF_READ_AS_INTEGER, which suppresses the default behavior of having the texture promote integer data to floating point data in the range [0, 1]. Note that texture with 32-bit integer format would not be promoted, regardless of whether or not this flag is specified;
• TRSF_NORMALIZED_COORDINATES, which suppresses the default behavior of having the texture coordinates range from [0, Dim) where Dim is the width or height of the CUDA array. Instead, the texture coordinates [0, 1.0) reference the entire breadth of the array dimension;
• TRSF_DISABLE_TRILINEAR_OPTIMIZATION, which disables any trilinear filtering optimizations. Trilinear optimizations improve texture filtering performance by allowing bilinear filtering on textures in scenarios where it can closely approximate the expected results.

Parameters:

hTexRef - texture reference

Flags - optional flags to set

ncuTexRefGetAddress

public static int ncuTexRefGetAddress(long pdptr,
 long hTexRef)

Unsafe version of: TexRefGetAddress

cuTexRefGetAddress

public static int cuTexRefGetAddress(PointerBuffer pdptr,
 long hTexRef)

Gets the address associated with a texture reference. (Deprecated)

Returns in *pdptr the base address bound to the texture reference hTexRef, or returns CUDA_ERROR_INVALID_VALUE if the texture reference is not bound to any device memory range.

Parameters:

pdptr - returned device address

hTexRef - texture reference

ncuTexRefGetArray

public static int ncuTexRefGetArray(long phArray,
 long hTexRef)

Unsafe version of: TexRefGetArray

cuTexRefGetArray

public static int cuTexRefGetArray(PointerBuffer phArray,
 long hTexRef)

Gets the array bound to a texture reference. (Deprecated)

Returns in *phArray the CUDA array bound to the texture reference hTexRef, or returns CUDA_ERROR_INVALID_VALUE if the texture reference is not bound to any CUDA array.

Parameters:

phArray - returned array

hTexRef - texture reference

ncuTexRefGetMipmappedArray

public static int ncuTexRefGetMipmappedArray(long phMipmappedArray,
 long hTexRef)

Unsafe version of: TexRefGetMipmappedArray

cuTexRefGetMipmappedArray

public static int cuTexRefGetMipmappedArray(PointerBuffer phMipmappedArray,
 long hTexRef)

Gets the mipmapped array bound to a texture reference. (Deprecated)

Returns in *phMipmappedArray the CUDA mipmapped array bound to the texture reference hTexRef, or returns CUDA_ERROR_INVALID_VALUE if the texture reference is not bound to any CUDA mipmapped array.

Parameters:

phMipmappedArray - returned mipmapped array

hTexRef - texture reference

ncuTexRefGetAddressMode

public static int ncuTexRefGetAddressMode(long pam,
 long hTexRef,
 int dim)

Unsafe version of: TexRefGetAddressMode

cuTexRefGetAddressMode

public static int cuTexRefGetAddressMode(IntBuffer pam,
 long hTexRef,
 int dim)

Gets the addressing mode used by a texture reference. (Deprecated)

Returns in *pam the addressing mode corresponding to the dimension dim of the texture reference hTexRef. Currently, the only valid value for dim are 0 and 1.

Parameters:

pam - returned addressing mode

hTexRef - texture reference

dim - dimension

ncuTexRefGetFilterMode

public static int ncuTexRefGetFilterMode(long pfm,
 long hTexRef)

Unsafe version of: TexRefGetFilterMode

cuTexRefGetFilterMode

public static int cuTexRefGetFilterMode(IntBuffer pfm,
 long hTexRef)

Gets the filter-mode used by a texture reference. (Deprecated)

Returns in *pfm the filtering mode of the texture reference hTexRef.

Parameters:

pfm - returned filtering mode

hTexRef - texture reference

ncuTexRefGetFormat

public static int ncuTexRefGetFormat(long pFormat,
 long pNumChannels,
 long hTexRef)

Unsafe version of: TexRefGetFormat

cuTexRefGetFormat

public static int cuTexRefGetFormat(IntBuffer pFormat,
 @Nullable
 IntBuffer pNumChannels,
 long hTexRef)

Gets the format used by a texture reference. (Deprecated)

Returns in *pFormat and *pNumChannels the format and number of components of the CUDA array bound to the texture reference hTexRef. If pFormat or pNumChannels is NULL, it will be ignored.

Parameters:

pFormat - returned format

pNumChannels - returned number of components

hTexRef - texture reference

ncuTexRefGetMipmapFilterMode

public static int ncuTexRefGetMipmapFilterMode(long pfm,
 long hTexRef)

Unsafe version of: TexRefGetMipmapFilterMode

cuTexRefGetMipmapFilterMode

public static int cuTexRefGetMipmapFilterMode(IntBuffer pfm,
 long hTexRef)

Gets the mipmap filtering mode for a texture reference. (Deprecated)

Returns the mipmap filtering mode in pfm that's used when reading memory through the texture reference hTexRef.

Parameters:

pfm - returned mipmap filtering mode

hTexRef - texture reference

ncuTexRefGetMipmapLevelBias

public static int ncuTexRefGetMipmapLevelBias(long pbias,
 long hTexRef)

Unsafe version of: TexRefGetMipmapLevelBias

cuTexRefGetMipmapLevelBias

public static int cuTexRefGetMipmapLevelBias(FloatBuffer pbias,
 long hTexRef)

Gets the mipmap level bias for a texture reference. (Deprecated)

Returns the mipmap level bias in pBias that's added to the specified mipmap level when reading memory through the texture reference hTexRef.

Parameters:

pbias - returned mipmap level bias

hTexRef - texture reference

ncuTexRefGetMipmapLevelClamp

public static int ncuTexRefGetMipmapLevelClamp(long pminMipmapLevelClamp,
 long pmaxMipmapLevelClamp,
 long hTexRef)

Unsafe version of: TexRefGetMipmapLevelClamp

cuTexRefGetMipmapLevelClamp

public static int cuTexRefGetMipmapLevelClamp(FloatBuffer pminMipmapLevelClamp,
 FloatBuffer pmaxMipmapLevelClamp,
 long hTexRef)

Gets the min/max mipmap level clamps for a texture reference. (Deprecated)

Returns the min/max mipmap level clamps in pminMipmapLevelClamp and pmaxMipmapLevelClamp that's used when reading memory through the texture reference hTexRef.

Parameters:

pminMipmapLevelClamp - returned mipmap min level clamp

pmaxMipmapLevelClamp - returned mipmap max level clamp

hTexRef - texture reference

ncuTexRefGetMaxAnisotropy

public static int ncuTexRefGetMaxAnisotropy(long pmaxAniso,
 long hTexRef)

Unsafe version of: TexRefGetMaxAnisotropy

cuTexRefGetMaxAnisotropy

public static int cuTexRefGetMaxAnisotropy(IntBuffer pmaxAniso,
 long hTexRef)

Gets the maximum anisotropy for a texture reference. (Deprecated)

Returns the maximum anisotropy in pmaxAniso that's used when reading memory through the texture reference hTexRef.

Parameters:

pmaxAniso - returned maximum anisotropy

hTexRef - texture reference

ncuTexRefGetBorderColor

public static int ncuTexRefGetBorderColor(long pBorderColor,
 long hTexRef)

Unsafe version of: TexRefGetBorderColor

cuTexRefGetBorderColor

public static int cuTexRefGetBorderColor(FloatBuffer pBorderColor,
 long hTexRef)

Gets the border color used by a texture reference. (Deprecated)

Returns in pBorderColor, values of the RGBA color used by the texture reference hTexRef. The color value is of type float and holds color components in the following sequence: pBorderColor[0] holds 'R' component pBorderColor[1] holds 'G' component pBorderColor[2] holds 'B' component pBorderColor[3] holds 'A' component

Parameters:

pBorderColor - returned Type and Value of RGBA color

hTexRef - texture reference

ncuTexRefGetFlags

public static int ncuTexRefGetFlags(long pFlags,
 long hTexRef)

Unsafe version of: TexRefGetFlags

cuTexRefGetFlags

public static int cuTexRefGetFlags(IntBuffer pFlags,
 long hTexRef)

Gets the flags used by a texture reference. (Deprecated)

Returns in *pFlags the flags of the texture reference hTexRef.

Parameters:

pFlags - returned flags

hTexRef - texture reference

ncuTexRefCreate

public static int ncuTexRefCreate(long pTexRef)

Unsafe version of: TexRefCreate

cuTexRefCreate

public static int cuTexRefCreate(PointerBuffer pTexRef)

Creates a texture reference. (Deprecated)

Creates a texture reference and returns its handle in *pTexRef. Once created, the application must call TexRefSetArray or TexRefSetAddress to associate the reference with allocated memory. Other texture reference functions are used to specify the format and interpretation (addressing, filtering, etc.) to be used when the memory is read through this texture reference.

Parameters:

pTexRef - returned texture reference

cuTexRefDestroy

public static int cuTexRefDestroy(long hTexRef)

Destroys a texture reference. (Deprecated)

Destroys the texture reference specified by hTexRef.

Parameters:

hTexRef - texture reference to destroy

cuSurfRefSetArray

public static int cuSurfRefSetArray(long hSurfRef,
 long hArray,
 int Flags)

Sets the CUDA array for a surface reference.Deprecated:

Sets the CUDA array hArray to be read and written by the surface reference hSurfRef. Any previous CUDA array state associated with the surface reference is superseded by this function. Flags must be set to 0. The CUDA_ARRAY3D_SURFACE_LDST flag must have been set for the CUDA array. Any CUDA array previously bound to hSurfRef is unbound.

Parameters:

hSurfRef - surface reference handle

hArray - CUDA array handle

Flags - set to 0

ncuSurfRefGetArray

public static int ncuSurfRefGetArray(long phArray,
 long hSurfRef)

Unsafe version of: SurfRefGetArray

cuSurfRefGetArray

public static int cuSurfRefGetArray(PointerBuffer phArray,
 long hSurfRef)

Passes back the CUDA array bound to a surface reference. (Deprecated)

Returns in *phArray the CUDA array bound to the surface reference hSurfRef, or returns CUDA_ERROR_INVALID_VALUE if the surface reference is not bound to any CUDA array.

Parameters:

phArray - surface reference handle

hSurfRef - surface reference handle

ncuTexObjectCreate

public static int ncuTexObjectCreate(long pTexObject,
 long pResDesc,
 long pTexDesc,
 long pResViewDesc)

Unsafe version of: TexObjectCreate

cuTexObjectCreate

public static int cuTexObjectCreate(LongBuffer pTexObject,
 CUDA_RESOURCE_DESC pResDesc,
 CUDA_TEXTURE_DESC pTexDesc,
 CUDA_RESOURCE_VIEW_DESC pResViewDesc)

Creates a texture object.

Creates a texture object and returns it in pTexObject. pResDesc describes the data to texture from. pTexDesc describes how the data should be sampled. pResViewDesc is an optional argument that specifies an alternate format for the data described by pResDesc, and also describes the subresource region to restrict access to when texturing. pResViewDesc can only be specified if the type of resource is a CUDA array or a CUDA mipmapped array.

Texture objects are only supported on devices of compute capability 3.0 or higher. Additionally, a texture object is an opaque value, and, as such, should only be accessed through CUDA API calls.

• If CUDA_RESOURCE_DESC::resType is set to RESOURCE_TYPE_ARRAY, CUDA_RESOURCE_DESC::res::array::hArray must be set to a valid CUDA array handle.
• If CUDA_RESOURCE_DESC::resType is set to RESOURCE_TYPE_MIPMAPPED_ARRAY, CUDA_RESOURCE_DESC::res::mipmap::hMipmappedArray must be set to a valid CUDA mipmapped array handle.
• If CUDA_RESOURCE_DESC::resType is set to RESOURCE_TYPE_LINEAR, CUDA_RESOURCE_DESC::res::linear::devPtr must be set to a valid device pointer, that is aligned to DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT. CUDA_RESOURCE_DESC::res::linear::format and CUDA_RESOURCE_DESC::res::linear::numChannels describe the format of each component and the number of components per array element. CUDA_RESOURCE_DESC::res::linear::sizeInBytes specifies the size of the array in bytes. The total number of elements in the linear address range cannot exceed DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH. The number of elements is computed as (sizeInBytes / (sizeof(format) * numChannels)).
• If CUDA_RESOURCE_DESC::resType is set to RESOURCE_TYPE_PITCH2D, CUDA_RESOURCE_DESC::res::pitch2D::devPtr must be set to a valid device pointer, that is aligned to DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT. CUDA_RESOURCE_DESC::res::pitch2D::format and CUDA_RESOURCE_DESC::res::pitch2D::numChannels describe the format of each component and the number of components per array element. CUDA_RESOURCE_DESC::res::pitch2D::width and CUDA_RESOURCE_DESC::res::pitch2D::height specify the width and height of the array in elements, and cannot exceed DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH and DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT respectively. CUDA_RESOURCE_DESC::res::pitch2D::pitchInBytes specifies the pitch between two rows in bytes and has to be aligned to DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT. Pitch cannot exceed DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH.
• flags must be set to zero.

• CUDA_TEXTURE_DESC::addressMode specifies the addressing mode for each dimension of the texture data. This is ignored if CUDA_RESOURCE_DESC::resType is RESOURCE_TYPE_LINEAR. Also, if the flag, TRSF_NORMALIZED_COORDINATES is not set, the only supported address mode is TR_ADDRESS_MODE_CLAMP.
• CUDA_TEXTURE_DESC::filterMode specifies the filtering mode to be used when fetching from the texture. This is ignored if CUDA_RESOURCE_DESC::resType is RESOURCE_TYPE_LINEAR.
• CUDA_TEXTURE_DESC::flags can be any combination of the following:
  • TRSF_READ_AS_INTEGER, which suppresses the default behavior of having the texture promote integer data to floating point data in the range [0, 1]. Note that texture with 32-bit integer format would not be promoted, regardless of whether or not this flag is specified.
  • TRSF_NORMALIZED_COORDINATES, which suppresses the default behavior of having the texture coordinates range from [0, Dim) where Dim is the width or height of the CUDA array. Instead, the texture coordinates [0, 1.0) reference the entire breadth of the array dimension; Note that for CUDA mipmapped arrays, this flag has to be set.
  • TRSF_DISABLE_TRILINEAR_OPTIMIZATION, which disables any trilinear filtering optimizations. Trilinear optimizations improve texture filtering performance by allowing bilinear filtering on textures in scenarios where it can closely approximate the expected results.
• CUDA_TEXTURE_DESC::maxAnisotropy specifies the maximum anisotropy ratio to be used when doing anisotropic filtering. This value will be clamped to the range [1,16].
• CUDA_TEXTURE_DESC::mipmapFilterMode specifies the filter mode when the calculated mipmap level lies between two defined mipmap levels.
• CUDA_TEXTURE_DESC::mipmapLevelBias specifies the offset to be applied to the calculated mipmap level.
• CUDA_TEXTURE_DESC::minMipmapLevelClamp specifies the lower end of the mipmap level range to clamp access to.
• CUDA_TEXTURE_DESC::maxMipmapLevelClamp specifies the upper end of the mipmap level range to clamp access to.

• CUDA_RESOURCE_VIEW_DESC::format specifies how the data contained in the CUDA array or CUDA mipmapped array should be interpreted. Note that this can incur a change in size of the texture data. If the resource view format is a block compressed format, then the underlying CUDA array or CUDA mipmapped array has to have a base of format AD_FORMAT_UNSIGNED_INT32. with 2 or 4 channels, depending on the block compressed format. For ex., BC1 and BC4 require the underlying CUDA array to have a format of AD_FORMAT_UNSIGNED_INT32 with 2 channels. The other BC formats require the underlying resource to have the same base format but with 4 channels.
• CUDA_RESOURCE_VIEW_DESC::width specifies the new width of the texture data. If the resource view format is a block compressed format, this value has to be 4 times the original width of the resource. For non block compressed formats, this value has to be equal to that of the original resource.
• CUDA_RESOURCE_VIEW_DESC::height specifies the new height of the texture data. If the resource view format is a block compressed format, this value has to be 4 times the original height of the resource. For non block compressed formats, this value has to be equal to that of the original resource.
• CUDA_RESOURCE_VIEW_DESC::depth specifies the new depth of the texture data. This value has to be equal to that of the original resource.
• CUDA_RESOURCE_VIEW_DESC::firstMipmapLevel specifies the most detailed mipmap level. This will be the new mipmap level zero. For non-mipmapped resources, this value has to be zero. CUDA_TEXTURE_DESC::minMipmapLevelClamp and CUDA_TEXTURE_DESC::maxMipmapLevelClamp will be relative to this value. For ex., if the firstMipmapLevel is set to 2, and a minMipmapLevelClamp of 1.2 is specified, then the actual minimum mipmap level clamp will be 3.2.
• CUDA_RESOURCE_VIEW_DESC::lastMipmapLevel specifies the least detailed mipmap level. For non-mipmapped resources, this value has to be zero.
• CUDA_RESOURCE_VIEW_DESC::firstLayer specifies the first layer index for layered textures. This will be the new layer zero. For non-layered resources, this value has to be zero.
• CUDA_RESOURCE_VIEW_DESC::lastLayer specifies the last layer index for layered textures. For non-layered resources, this value has to be zero.

Parameters:

pTexObject - texture object to create

pResDesc - resource descriptor

pTexDesc - texture descriptor

pResViewDesc - resource view descriptor

cuTexObjectDestroy

public static int cuTexObjectDestroy(long texObject)

Destroys a texture object.

Destroys the texture object specified by texObject.

Parameters:

texObject - texture object to destroy

ncuTexObjectGetResourceDesc

public static int ncuTexObjectGetResourceDesc(long pResDesc,
 long texObject)

Unsafe version of: TexObjectGetResourceDesc

cuTexObjectGetResourceDesc

public static int cuTexObjectGetResourceDesc(CUDA_RESOURCE_DESC pResDesc,
 long texObject)

Returns a texture object's resource descriptor.

Returns the resource descriptor for the texture object specified by texObject.

Parameters:

pResDesc - resource descriptor

texObject - texture object

ncuTexObjectGetTextureDesc

public static int ncuTexObjectGetTextureDesc(long pTexDesc,
 long texObject)

Unsafe version of: TexObjectGetTextureDesc

cuTexObjectGetTextureDesc

public static int cuTexObjectGetTextureDesc(CUDA_TEXTURE_DESC pTexDesc,
 long texObject)

Returns a texture object's texture descriptor.

Returns the texture descriptor for the texture object specified by texObject.

Parameters:

pTexDesc - texture descriptor

texObject - texture object

ncuTexObjectGetResourceViewDesc

public static int ncuTexObjectGetResourceViewDesc(long pResViewDesc,
 long texObject)

Unsafe version of: TexObjectGetResourceViewDesc

cuTexObjectGetResourceViewDesc

public static int cuTexObjectGetResourceViewDesc(CUDA_RESOURCE_VIEW_DESC pResViewDesc,
 long texObject)

Returns a texture object's resource view descriptor.

Returns the resource view descriptor for the texture object specified by texObject. If no resource view was set for texObject, the CUDA_ERROR_INVALID_VALUE is returned.

Parameters:

pResViewDesc - resource view descriptor

texObject - texture object

ncuSurfObjectCreate

public static int ncuSurfObjectCreate(long pSurfObject,
 long pResDesc)

Unsafe version of: SurfObjectCreate

cuSurfObjectCreate

public static int cuSurfObjectCreate(LongBuffer pSurfObject,
 CUDA_RESOURCE_DESC pResDesc)

Creates a surface object.

Creates a surface object and returns it in pSurfObject. pResDesc describes the data to perform surface load/stores on. CUDA_RESOURCE_DESC::resType must be RESOURCE_TYPE_ARRAY and CUDA_RESOURCE_DESC::res::array::hArray must be set to a valid CUDA array handle. CUDA_RESOURCE_DESC::flags must be set to zero.

Surface objects are only supported on devices of compute capability 3.0 or higher. Additionally, a surface object is an opaque value, and, as such, should only be accessed through CUDA API calls.

Parameters:

pSurfObject - surface object to create

pResDesc - resource descriptor

cuSurfObjectDestroy

public static int cuSurfObjectDestroy(long surfObject)

Destroys a surface object.

Destroys the surface object specified by surfObject.

Parameters:

surfObject - surface object to destroy

ncuSurfObjectGetResourceDesc

public static int ncuSurfObjectGetResourceDesc(long pResDesc,
 long surfObject)

Unsafe version of: SurfObjectGetResourceDesc

cuSurfObjectGetResourceDesc

public static int cuSurfObjectGetResourceDesc(CUDA_RESOURCE_DESC pResDesc,
 long surfObject)

Returns a surface object's resource descriptor.

Returns the resource descriptor for the surface object specified by surfObject.

Parameters:

pResDesc - resource descriptor

surfObject - surface object

ncuDeviceCanAccessPeer

public static int ncuDeviceCanAccessPeer(long canAccessPeer,
 int dev,
 int peerDev)

Unsafe version of: DeviceCanAccessPeer

cuDeviceCanAccessPeer

public static int cuDeviceCanAccessPeer(IntBuffer canAccessPeer,
 int dev,
 int peerDev)

Queries if a device may directly access a peer device's memory.

Returns in *canAccessPeer a value of 1 if contexts on dev are capable of directly accessing memory from contexts on peerDev and 0 otherwise. If direct access of peerDev from dev is possible, then access may be enabled on two specific contexts by calling CtxEnablePeerAccess.

Parameters:

canAccessPeer - returned access capability

dev - device from which allocations on peerDev are to be directly accessed

peerDev - device on which the allocations to be directly accessed by dev reside

cuCtxEnablePeerAccess

public static int cuCtxEnablePeerAccess(long peerContext,
 int Flags)

Enables direct access to memory allocations in a peer context.

If both the current context and peerContext are on devices which support unified addressing (as may be queried using DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING) and same major compute capability, then on success all allocations from peerContext will immediately be accessible by the current context. See ref for additional details.

Note that access granted by this call is unidirectional and that in order to access memory from the current context in peerContext, a separate symmetric call to CtxEnablePeerAccess is required.

Note that there are both device-wide and system-wide limitations per system configuration, as noted in the CUDA Programming Guide under the section "Peer-to-Peer Memory Access".

Returns CUDA_ERROR_PEER_ACCESS_UNSUPPORTED if DeviceCanAccessPeer indicates that the CUdevice of the current context cannot directly access memory from the CUdevice of peerContext.

Returns CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED if direct access of peerContext from the current context has already been enabled.

Returns CUDA_ERROR_TOO_MANY_PEERS if direct peer access is not possible because hardware resources required for peer access have been exhausted.

Returns CUDA_ERROR_INVALID_CONTEXT if there is no current context, peerContext is not a valid context, or if the current context is peerContext.

Returns CUDA_ERROR_INVALID_VALUE if Flags is not 0.

Parameters:

peerContext - peer context to enable direct access to from the current context

Flags - reserved for future use and must be set to 0

cuCtxDisablePeerAccess

public static int cuCtxDisablePeerAccess(long peerContext)

Disables direct access to memory allocations in a peer context and unregisters any registered allocations.

Returns CUDA_ERROR_PEER_ACCESS_NOT_ENABLED if direct peer access has not yet been enabled from peerContext to the current context.

Returns CUDA_ERROR_INVALID_CONTEXT if there is no current context, or if peerContext is not a valid context.

Parameters:

peerContext - peer context to disable direct access to

ncuDeviceGetP2PAttribute

public static int ncuDeviceGetP2PAttribute(long value,
 int attrib,
 int srcDevice,
 int dstDevice)

Unsafe version of: DeviceGetP2PAttribute

cuDeviceGetP2PAttribute

public static int cuDeviceGetP2PAttribute(IntBuffer value,
 int attrib,
 int srcDevice,
 int dstDevice)

Queries attributes of the link between two devices.

Returns in *value the value of the requested attribute attrib of the link between srcDevice and dstDevice. The supported attributes are:

• DEVICE_P2P_ATTRIBUTE_PERFORMANCE_RANK: A relative value indicating the performance of the link between two devices.
• DEVICE_P2P_ATTRIBUTE_ACCESS_SUPPORTED P2P: 1 if P2P Access is enable.
• DEVICE_P2P_ATTRIBUTE_NATIVE_ATOMIC_SUPPORTED: 1 if Atomic operations over the link are supported.
• DEVICE_P2P_ATTRIBUTE_CUDA_ARRAY_ACCESS_SUPPORTED: 1 if cudaArray can be accessed over the link.

Returns CUDA_ERROR_INVALID_DEVICE if srcDevice or dstDevice are not valid or if they represent the same device.

Returns CUDA_ERROR_INVALID_VALUE if attrib is not valid or if value is a null pointer.

Parameters:

value - returned value of the requested attribute

attrib - the requested attribute of the link between srcDevice and dstDevice

srcDevice - the source device of the target link

dstDevice - the destination device of the target link

cuGraphicsUnregisterResource

public static int cuGraphicsUnregisterResource(long resource)

Unregisters a graphics resource for access by CUDA.

Unregisters the graphics resource resource so it is not accessible by CUDA unless registered again.

If resource is invalid then CUDA_ERROR_INVALID_HANDLE is returned.

Parameters:

resource - resource to unregister

ncuGraphicsSubResourceGetMappedArray

public static int ncuGraphicsSubResourceGetMappedArray(long pArray,
 long resource,
 int arrayIndex,
 int mipLevel)

Unsafe version of: GraphicsSubResourceGetMappedArray

cuGraphicsSubResourceGetMappedArray

public static int cuGraphicsSubResourceGetMappedArray(PointerBuffer pArray,
 long resource,
 int arrayIndex,
 int mipLevel)

Get an array through which to access a subresource of a mapped graphics resource.

Returns in *pArray an array through which the subresource of the mapped graphics resource resource which corresponds to array index arrayIndex and mipmap level mipLevel may be accessed. The value set in *pArray may change every time that resource is mapped.

If resource is not a texture then it cannot be accessed via an array and CUDA_ERROR_NOT_MAPPED_AS_ARRAY is returned. If arrayIndex is not a valid array index for resource then CUDA_ERROR_INVALID_VALUE is returned. If mipLevel is not a valid mipmap level for resource then CUDA_ERROR_INVALID_VALUE is returned. If resource is not mapped then CUDA_ERROR_NOT_MAPPED is returned.

Parameters:

pArray - returned array through which a subresource of resource may be accessed

resource - mapped resource to access

arrayIndex - array index for array textures or cubemap face index as defined by CUarray_cubemap_face for cubemap textures for the subresource to access

mipLevel - mipmap level for the subresource to access

ncuGraphicsResourceGetMappedMipmappedArray

public static int ncuGraphicsResourceGetMappedMipmappedArray(long pMipmappedArray,
 long resource)

Unsafe version of: GraphicsResourceGetMappedMipmappedArray

cuGraphicsResourceGetMappedMipmappedArray

public static int cuGraphicsResourceGetMappedMipmappedArray(PointerBuffer pMipmappedArray,
 long resource)

Get a mipmapped array through which to access a mapped graphics resource.

Returns in *pMipmappedArray a mipmapped array through which the mapped graphics resource resource. The value set in *pMipmappedArray may change every time that resource is mapped.

If resource is not a texture then it cannot be accessed via a mipmapped array and CUDA_ERROR_NOT_MAPPED_AS_ARRAY is returned. If resource is not mapped then CUDA_ERROR_NOT_MAPPED is returned.

Parameters:

pMipmappedArray - returned mipmapped array through which resource may be accessed

resource - mapped resource to access

ncuGraphicsResourceGetMappedPointer

public static int ncuGraphicsResourceGetMappedPointer(long pDevPtr,
 long pSize,
 long resource)

Unsafe version of: GraphicsResourceGetMappedPointer

cuGraphicsResourceGetMappedPointer

public static int cuGraphicsResourceGetMappedPointer(PointerBuffer pDevPtr,
 PointerBuffer pSize,
 long resource)

Get a device pointer through which to access a mapped graphics resource.

Returns in *pDevPtr a pointer through which the mapped graphics resource resource may be accessed. Returns in pSize the size of the memory in bytes which may be accessed from that pointer. The value set in pPointer may change every time that resource is mapped.

If resource is not a buffer then it cannot be accessed via a pointer and CUDA_ERROR_NOT_MAPPED_AS_POINTER is returned. If resource is not mapped then CUDA_ERROR_NOT_MAPPED is returned. *

Parameters:

pDevPtr - returned pointer through which resource may be accessed

pSize - returned size of the buffer accessible starting at *pPointer

resource - mapped resource to access

cuGraphicsResourceSetMapFlags

public static int cuGraphicsResourceSetMapFlags(long resource,
 int flags)

Set usage flags for mapping a graphics resource.

Set flags for mapping the graphics resource resource.

Changes to flags will take effect the next time resource is mapped. The flags argument may be any of the following:

• GRAPHICS_MAP_RESOURCE_FLAGS_NONE: Specifies no hints about how this resource will be used. It is therefore assumed that this resource will be read from and written to by CUDA kernels. This is the default value.
• GRAPHICS_MAP_RESOURCE_FLAGS_READ_ONLY: Specifies that CUDA kernels which access this resource will not write to this resource.
• GRAPHICS_MAP_RESOURCE_FLAGS_WRITE_DISCARD: Specifies that CUDA kernels which access this resource will not read from this resource and will write over the entire contents of the resource, so none of the data previously stored in the resource will be preserved.

If resource is presently mapped for access by CUDA then CUDA_ERROR_ALREADY_MAPPED is returned. If flags is not one of the above values then CUDA_ERROR_INVALID_VALUE is returned.

Parameters:

resource - registered resource to set flags for

flags - parameters for resource mapping

ncuGraphicsMapResources

public static int ncuGraphicsMapResources(int count,
 long resources,
 long hStream)

Unsafe version of: GraphicsMapResources

Parameters:

count - number of resources to map

cuGraphicsMapResources

public static int cuGraphicsMapResources(PointerBuffer resources,
 long hStream)

Map graphics resources for access by CUDA.

Maps the count graphics resources in resources for access by CUDA.

The resources in resources may be accessed by CUDA until they are unmapped. The graphics API from which resources were registered should not access any resources while they are mapped by CUDA. If an application does so, the results are undefined.

This function provides the synchronization guarantee that any graphics calls issued before GraphicsMapResources will complete before any subsequent CUDA work issued in stream begins.

If resources includes any duplicate entries then CUDA_ERROR_INVALID_HANDLE is returned. If any of resources are presently mapped for access by CUDA then CUDA_ERROR_ALREADY_MAPPED is returned.

Parameters:

resources - resources to map for CUDA usage

hStream - stream with which to synchronize

ncuGraphicsUnmapResources

public static int ncuGraphicsUnmapResources(int count,
 long resources,
 long hStream)

Unsafe version of: GraphicsUnmapResources

Parameters:

count - number of resources to unmap

cuGraphicsUnmapResources

public static int cuGraphicsUnmapResources(PointerBuffer resources,
 long hStream)

Unmap graphics resources.

Unmaps the count graphics resources in resources.

Once unmapped, the resources in resources may not be accessed by CUDA until they are mapped again.

This function provides the synchronization guarantee that any CUDA work issued in stream before GraphicsUnmapResources will complete before any subsequently issued graphics work begins.

If resources includes any duplicate entries then CUDA_ERROR_INVALID_HANDLE is returned. If any of resources are not presently mapped for access by CUDA then CUDA_ERROR_NOT_MAPPED is returned.

Parameters:

resources - resources to unmap

hStream - stream with which to synchronize

ncuGetProcAddress

public static int ncuGetProcAddress(long symbol,
 long pfn,
 int cudaVersion,
 long flags)

Unsafe version of: GetProcAddress

cuGetProcAddress

public static int cuGetProcAddress(ByteBuffer symbol,
 PointerBuffer pfn,
 int cudaVersion,
 long flags)

Returns the requested driver API function pointer.

Returns in **pfn the address of the CUDA driver function for the requested CUDA version and flags.

The CUDA version is specified as (1000 * major + 10 * minor), so CUDA 11.2 should be specified as 11020. For a requested driver symbol, if the specified CUDA version is greater than or equal to the CUDA version in which the driver symbol was introduced, this API will return the function pointer to the corresponding versioned function.

The pointer returned by the API should be cast to a function pointer matching the requested driver function's definition in the API header file. The function pointer typedef can be picked up from the corresponding typedefs header file. For example, cudaTypedefs.h consists of function pointer typedefs for driver APIs defined in cuda.h.

The API will return CUDA_ERROR_NOT_FOUND if the requested driver function is not supported on the platform, no ABI compatible driver function exists for the specified cudaVersion or if the driver symbol is invalid.

The requested flags can be:

• GET_PROC_ADDRESS_DEFAULT: This is the default mode. This is equivalent to GET_PROC_ADDRESS_PER_THREAD_DEFAULT_STREAM if the code is compiled with --default-stream per-thread compilation flag or the macro CUDA_API_PER_THREAD_DEFAULT_STREAM is defined; GET_PROC_ADDRESS_LEGACY_STREAM otherwise.
• GET_PROC_ADDRESS_LEGACY_STREAM: This will enable the search for all driver symbols that match the requested driver symbol name except the corresponding per-thread versions.
• GET_PROC_ADDRESS_PER_THREAD_DEFAULT_STREAM: This will enable the search for all driver symbols that match the requested driver symbol name including the per-thread versions. If a per-thread version is not found, the API will return the legacy version of the driver function.

Parameters:

symbol - the base name of the driver API function to look for. As an example, for the driver API cuMemAlloc_v2(), symbol would be cuMemAlloc and cudaVersion would be the ABI compatible CUDA version for the _v2 variant.

pfn - location to return the function pointer to the requested driver function

cudaVersion - the CUDA version to look for the requested driver symbol

flags - flags to specify search options

cuGetProcAddress

public static int cuGetProcAddress(CharSequence symbol,
 PointerBuffer pfn,
 int cudaVersion,
 long flags)

Returns the requested driver API function pointer.

Returns in **pfn the address of the CUDA driver function for the requested CUDA version and flags.

The CUDA version is specified as (1000 * major + 10 * minor), so CUDA 11.2 should be specified as 11020. For a requested driver symbol, if the specified CUDA version is greater than or equal to the CUDA version in which the driver symbol was introduced, this API will return the function pointer to the corresponding versioned function.

The pointer returned by the API should be cast to a function pointer matching the requested driver function's definition in the API header file. The function pointer typedef can be picked up from the corresponding typedefs header file. For example, cudaTypedefs.h consists of function pointer typedefs for driver APIs defined in cuda.h.

The API will return CUDA_ERROR_NOT_FOUND if the requested driver function is not supported on the platform, no ABI compatible driver function exists for the specified cudaVersion or if the driver symbol is invalid.

The requested flags can be:

• GET_PROC_ADDRESS_DEFAULT: This is the default mode. This is equivalent to GET_PROC_ADDRESS_PER_THREAD_DEFAULT_STREAM if the code is compiled with --default-stream per-thread compilation flag or the macro CUDA_API_PER_THREAD_DEFAULT_STREAM is defined; GET_PROC_ADDRESS_LEGACY_STREAM otherwise.
• GET_PROC_ADDRESS_LEGACY_STREAM: This will enable the search for all driver symbols that match the requested driver symbol name except the corresponding per-thread versions.
• GET_PROC_ADDRESS_PER_THREAD_DEFAULT_STREAM: This will enable the search for all driver symbols that match the requested driver symbol name including the per-thread versions. If a per-thread version is not found, the API will return the legacy version of the driver function.

Parameters:

symbol - the base name of the driver API function to look for. As an example, for the driver API cuMemAlloc_v2(), symbol would be cuMemAlloc and cudaVersion would be the ABI compatible CUDA version for the _v2 variant.

pfn - location to return the function pointer to the requested driver function

cudaVersion - the CUDA version to look for the requested driver symbol

flags - flags to specify search options

ncuGetExportTable

public static int ncuGetExportTable(long ppExportTable,
 long pExportTableId)

cuGetExportTable

public static int cuGetExportTable(PointerBuffer ppExportTable,
 CUuuid pExportTableId)